Anti-ATS Evaluatorv1.3

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.2] There is some proximity via LLM integration and building an LLM-driven scoring tool, which suggests applied AI exposure. However, the role requires deep hands-on AI architecture (RAG, embeddings, vector DBs), MLOps, and typically advanced academic background/AI track record not evidenced here. **Strengths:** Built an LLM-integrated production tool, Strong problem framing and stakeholder communication, Systems/automation orientation **Critical Gaps:** Production AI architecture (RAG/embeddings/vector DB + MLOps) not demonstrated **Inferred Skills:** LLM application integration, Unstructured text processing, Applied automation and evaluation/scoring mindset **Missing Required:** Deep expertise with LLMs/embeddings/RAG/agents, Vector database implementation, MLOps pipelines + monitoring, AI/ML production system experience (explicit) **Missing Nice-to-Have:** Publications/open-source contributions, Distributed/GPU optimization

[ANALYSIS_REPORT] **LOW** [2.5-Pro] Candidate has relevant experience with Python and LLMs, but this role requires a specific production environment of Kubernetes/OpenShift and data streaming with Kafka. These are critical, specified gaps in the candidate's containerization and infrastructure experience. **Strengths:** Domínio de Python para construção de APIs, Conceptual understanding of GenAI in production, Git, CI/CD **Critical Gaps:** Experiência com Kubernetes / OpenShift em produção **Missing Required:** Experiência com containers (Kubernetes / OpenShift), Experiência em Machine Learning clássico, Experiência com Kafka, Experiência com Elasticsearch / OpenSearch **Missing Nice-to-Have:** RAG, OpenShift AI, Data Governance

[ANALYSIS_REPORT] **MEDIUM** [2.5-Pro] Candidate is an extremely strong backend GenAI developer, fitting most of the Python, AI, and AWS requirements perfectly. However, the role is explicitly 'Full Stack' with deep and specific requirements for frontend development in React, which is a critical gap in his backend-focused profile. **Strengths:** Python avançado, Experiência prática com LLMs e arquiteturas RAG, Experiência com AWS e Docker **Critical Gaps:** Frontend development with React **Inferred Skills:** MLOps cycle understanding, Feature Engineering **Missing Required:** Experiência desenvolvendo aplicações web modernas utilizando React **Missing Nice-to-Have:** Certificação AWS, Terraform

[ANALYSIS_REPORT] **MEDIUM** [2.5-Pro] An excellent fit for the backend portion of the role, with direct experience in Python, Node.js, and LLM integration. However, the 'Full Stack' requirement includes Next.js (a React framework) and GCP, which are critical gaps for the candidate. **Strengths:** Python avançado (FastAPI, LLMs), Node.js, Security mindset (LGPD mentioned in resume) **Critical Gaps:** Next.js (Frontend Framework), GCP (Required Cloud Platform) **Inferred Skills:** NLP services, RAG pipelines **Missing Required:** GCP, Next.js **Missing Nice-to-Have:** pgvector, Weaviate, Elastic

[ANALYSIS_REPORT] **LOW** [2.5-Pro] This is a highly specialized role requiring deep expertise in a modern MLOps and Big Data stack that the candidate does not have. There are multiple critical gaps, including Spark, Kubernetes, Kubeflow, and Airflow, making this a non-match. **Strengths:** Python e SQL avançados, Conceptual knowledge of RAG, AWS Fundamentals **Critical Gaps:** Spark / PySpark, Kubernetes (EKS), Kubeflow / MLflow **Missing Required:** Apache Airflow, Spark / PySpark, Kubernetes (EKS), Kubeflow MLflow, Feature Stores **Missing Nice-to-Have:** AI Agents, Prometheus, Grafana

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.2] The candidate shows relevant building blocks: Python listed, LLM integration, API/scraping-driven ingestion, and shipping production automation. The gaps are explicit agent/RAG stacks (MCPs, frameworks), MLOps/deployment practices, and demonstrated years focusing on AI/ML systems. **Strengths:** Shipping practical automation systems, LLM integration experience, Strong communication and execution bias **Critical Gaps:** End-to-end AI agent/RAG production experience not demonstrated **Inferred Skills:** LLM integration into a product workflow, Tooling/automation around scoring/evaluation, Unstructured text ingestion **Missing Required:** Hands-on experience with LLM agent/RAG pipelines or autonomous agent frameworks, MLOps + model deployment practices (explicit), 8+ years software engineering focused on AI/ML systems (explicit) **Missing Nice-to-Have:** Reinforcement learning, AI safety/alignment, Open-source contributions

[ANALYSIS_REPORT] **TOP** [2.5-Pro] Candidate is a perfect technical and conceptual fit, with demonstrated experience in all key areas: low-code automation (n8n equivalent), LLM integration, RAG concepts, and deploying applications. The role of building autonomous agents is precisely what he has been doing in his own venture. The only blocker is the on-site location requirement. **Strengths:** Domínio no uso de LLMs via API com prompts complexos, Experiência sólida com automação (n8n/Zapier), Raciocínio lógico forte para resolver problemas de negócio via automação **Critical Gaps:** Location requirement (Presencial — Balneário Camboriú/SC) **Inferred Skills:** VPS and Docker deployment, Product development of AI agents **Missing Nice-to-Have:** Arquitetura de microsserviços, Bancos de dados NoSQL, Experiência com vetores, embeddings

[ANALYSIS_REPORT] **TOP** [2.5-Pro] An extremely strong candidate for a Machine Learning Engineer role. His proven ability to single-handedly build, deploy, and operate an AI-powered application demonstrates mastery of the end-to-end lifecycle. Though missing Terraform, his fast-learning track record and deep practical skills make this a minor gap. **Strengths:** Python (fluente), Hands-on experience with GenAI pipelines (RAG), Proven ability to deliver models to production environments **Inferred Skills:** CI/CD pipeline implementation, Monitoring AI agents, Docker image creation **Missing Required:** Experiência com Terraform **Missing Nice-to-Have:** Experiência com GitOps, Certificação em Nuvem

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] Strong match on GenAI/LLM concepts and backend thinking, but the core stack for this role is Java/Kotlin with Spring/Quarkus, which is entirely absent from the profile. Most of the candidate’s recent experience is in Python/Node.js and automation, so migrating to a Java 21+/Spring ecosystem would require significant ramp-up. **Strengths:** GenAI/LLM integration in production-like systems, Ability to translate complex business logic into implementable technical specifications, Design of autonomous, low-maintenance operational systems **Critical Gaps:** No hands-on experience with the core Java/Kotlin + Spring/Quarkus backend stack that is central to the role **Inferred Skills:** Backend architecture using Node.js and Python, LLM integration and prompt design for production-like tools, Data validation and governance in ERP and inventory systems, System observability and cost-awareness mindset from running automated operations **Missing Required:** Production Java 21+ or Kotlin experience, Experience with Spring Boot 3.x or Quarkus, Experience with message queues like Kafka, SQS or RabbitMQ, Hands-on use of vector databases for embeddings and semantic search, Experience with Spring AI and/or LangChain4j **Missing Nice-to-Have:** Experience with SaaS B2B multi-tenant systems, Experience with event-driven architectures, Kubernetes and observability stack (e.g., OpenTelemetry)

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5.1] Very strong fit on senior software engineering, GenAI/LLM flows, and platform mindset, with a clear track record of building autonomous systems and AI-enabled tools. Main gaps are lack of explicit experience running an internal AI platform across multiple product squads and limited depth in a specific cloud provider stack. **Strengths:** Practical GenAI/LLM experience aligned with platform use cases, Senior-level ownership and design of complex, autonomous systems, Excellent communication bridging product, business and engineering **Inferred Skills:** Platform thinking from designing an autonomous e-commerce supply chain and operations, LLM-based agent and workflow design from intelligence tools and self-hosted clusters, Governance, guardrails and observability mindset from weekly status, risks and decisions rituals, Strong cross-functional communication with both technical and non-technical stakeholders **Missing Required:** Explicit experience implementing LLM agents and RAG at scale in multi-team environments **Missing Nice-to-Have:** Experience with AWS and/or GCP, Previous work in regulated environments (fintech, healthtech, insurance), Experience building developer tools or internal engineering platforms

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5.1] Good fit for a generalist Machine Learning/AI Engineer role, with strong quantitative background from trading, forecasting, and analytics plus solid Python/SQL skills. Main gaps are the absence of explicit ML framework usage and formalized ML deployment/monitoring pipelines in the resume. **Strengths:** Strong quantitative foundation from trading and supply chain analytics, Experience building data-driven systems that impact real financial and operational outcomes, Excellent English and readiness to collaborate with international teams **Inferred Skills:** Time-series and volatility modeling from algorithmic trading work, Statistical forecasting and demand modeling from supply chain analytics, Python-based data analysis and automation, Ability to translate business requirements into quantitative models and dashboards **Missing Nice-to-Have:** Explicitly labeled ML projects deployed and maintained in production, Explicit mention of ML model monitoring and validation best practices

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5.1] Reasonable match on Python, SQL, statistics-heavy work and applied AI through trading and LLM integration, but lacking explicit experience with standard ML frameworks and containerization. Cloud/MLOps exposure is also not clearly demonstrated. **Strengths:** Strong Python and SQL foundation, Proven ability to turn analytics into operational impact (ERP fixes, inventory optimization), Clear communication and stakeholder-bridging skills **Inferred Skills:** Statistical reasoning from volatility-based trading strategies and demand forecasting, Python-based data processing and automation, LLM integration and prompt design for tooling, Ability to explain complex technical trade-offs to both technical and non-technical stakeholders **Missing Required:** Hands-on experience with mainstream ML libraries (TensorFlow, PyTorch, scikit-learn, statsmodels), Experience deploying ML models in containers (e.g., Docker) into production **Missing Nice-to-Have:** Experience with cloud platforms such as AWS or Azure for ML workloads, Experience in computer vision and NLP using modern models, Prior work in public sector or security-related domains

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.2] Some relevant signals exist from quantitative development and building operational decision systems, plus Python is listed in the stack. But the role is explicitly ML engineering (productionizing models, MLOps tooling, ML services, monitoring/retraining) which is not supported by concrete resume evidence. **Strengths:** Strong analytical thinking and systemization, Communication/translation between business and engineers, SQL/data reasoning and data quality focus **Critical Gaps:** Production ML model lifecycle ownership (train→deploy→monitor→retrain) not demonstrated **Inferred Skills:** Quantitative system design (rules/monitoring dashboards), Data analysis and KPI instrumentation, Automation mindset **Missing Required:** Solid ML background, Proven experience productionizing ML models, MLOps tools/platforms experience, Cloud-based ML infrastructure skills (explicit) **Missing Nice-to-Have:** Deep learning, LLMs/AI agents, Spark, Java

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] While the candidate has solid Python/SQL and real-world ETL-style experience, this role demands deep, hands-on AWS data engineering (Glue, Lambda, Step Functions, Redshift) that is not present. The profile is more systems/AI generalist than senior AWS data engineer. **Strengths:** Strong SQL and Python background, Proven success fixing messy operational data environments, Good understanding of business-facing data use cases **Critical Gaps:** No demonstrated experience as a senior AWS-centric data engineer building managed cloud data pipelines **Inferred Skills:** ETL-style data cleaning and validation in ERP (TOTVS/Protheus), SQL-based analytics and KPI dashboards, Python scripting for automation and API integrations, Experience aligning data work with business cost and operational outcomes **Missing Required:** Practical experience with AWS Glue, Lambda, Step Functions, S3, Athena and Redshift (or close equivalents), Demonstrated senior data engineer role focused on AWS data platforms **Missing Nice-to-Have:** Experience with SNS/SQS or EventBridge, Experience with event-driven data architectures, Experience with Data Hub/Data Mesh/Serving layers, Data observability tooling

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] Good Python/SQL and data intuition, but lacks hands-on GCP (BigQuery, Cloud Functions, Cloud Storage) and modern orchestration tools like Airflow/Prefect/dbt that are central to this Staff Data Engineer role. The candidate’s experience is more in systems and business operations than in leading a GCP-based data platform. **Strengths:** Strong data intuition and governance mindset, Experience supporting analytics and decision-making through better data flows, Leadership exposure with stakeholders even if not titled as Staff **Critical Gaps:** No concrete experience leading a GCP-based data engineering chapter or large-scale data platform **Inferred Skills:** Python and SQL for data manipulation, Design of robust, auditable workflows in ERPs and e-commerce operations, API-based data integrations **Missing Required:** Hands-on GCP experience (BigQuery, Cloud Functions, Cloud Storage), Experience with pipeline orchestrators such as Airflow, Prefect or Dagster, Experience with dbt transformations in production **Missing Nice-to-Have:** Experience mentoring a team of data engineers on a modern cloud stack, Exposure to advanced analytics and ML workloads on top of the data platform

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] Solid Python/SQL and data governance experience, but the role requires advanced big data tooling on AWS (PySpark/Hadoop/Glue, Redshift, SAP Datasphere) plus ML/DL/NLP, which are not present. The candidate’s background is more in operational data and AI tooling than in large-scale AWS data engineering. **Strengths:** Solid programming and analytics foundation, Experience with high-criticality operational data in supply chain and finance, Strong English and communication skills **Critical Gaps:** No demonstrated background as a senior big data engineer on AWS with large-scale pipelines and ML workloads **Inferred Skills:** Python/SQL programming for data processing, Data quality and governance mindset from ERP remediation and validation rules, Some exposure to NLP/LLM concepts via LLM integrations **Missing Required:** Hands-on experience with AWS for data engineering (Redshift, Glue, Data Lake), Experience with big data frameworks such as PySpark or Hadoop, Practical ML/DL and NLP work in production **Missing Nice-to-Have:** Experience in large on-site corporate environments with strict governance, Experience leading or mentoring other data engineers

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] The candidate has good Python/SQL and data modeling skills, but this role is tightly focused on GCP data engineering (BigQuery, Dataflow, Composer, DataPlex/DataForm) and medalhão architecture, none of which appear in the profile. Experience is concentrated in ERP/e-commerce rather than in GCP-centric data platforms. **Strengths:** Good data modeling and business analytics experience, Automation mindset for reducing manual work in operations, Ability to collaborate with business stakeholders around data needs **Critical Gaps:** No hands-on experience with GCP-centric data engineering or BigQuery-based architectures **Inferred Skills:** Python scripting for automation, SQL-based analytics and reporting, General understanding of data governance and quality from ERP projects **Missing Required:** Solid experience with core GCP data tools (BigQuery, Composer, Dataflow, DataPlex), Experience building and operating medalhão data lake architectures, Automation/orchestration of pipelines in GCP using Python **Missing Nice-to-Have:** AWS ecosystem experience beyond fundamentals, Terraform or CloudFormation for infrastructure as code, Experience in DevSecOps and DataOps practices, Projects involving cloud-to-cloud migrations or integrations

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.2] Good overlap on Python/SQL foundations, ETL-like workflow thinking, and data validation/quality controls. The role, however, is centered on Azure Databricks/Spark/ADF/ADLS and cloud/on-prem big-data pipeline operations, which are not shown. **Strengths:** Data quality and governance mindset, Automation and operational ownership, Strong communication in cross-functional settings **Critical Gaps:** Databricks/Spark pipeline implementation not demonstrated **Inferred Skills:** Data validation rules and controls, Pipeline-style automation for operations, Stakeholder collaboration for requirements **Missing Required:** Databricks + Spark data pipelines, ADF/ADLS experience, Pipeline automation/orchestration (explicit) **Missing Nice-to-Have:** Azure DevOps, Leading design decisions (explicit technical direction in data stack)

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] This role requires deep experience with AWS big data (Spark, Hadoop, Airflow, Kafka, Glue, Redshift, Docker/Kubernetes), which is absent, while the candidate’s experience is in smaller-scale automation, ERPs and AI tooling. The domain focus is quite different from large-scale cloud data engineering. **Strengths:** Strong generalist engineering and analytics profile, Experience integrating disparate operational data sources, Comfort working across business and technical contexts **Critical Gaps:** No direct experience with large-scale AWS big data ecosystems or distributed processing (Spark/Hadoop) **Inferred Skills:** Python scripting for automation and data handling, SQL and relational data modeling, Web scraping and API integrations as data sources **Missing Required:** 5+ years specifically in data engineering roles, Hands-on experience with Spark, Airflow and Kafka, Experience building data lakes/data lakehouses on AWS **Missing Nice-to-Have:** Experience with SAP S/4 HANA or SAP Analytics Cloud, Knowledge of Aecorsoft Data Integrator, Experience with BI tools (Power BI, Tableau, Qlik, MicroStrategy), Terraform and monitoring tools like New Relic

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.2] The resume aligns with the general problem space (data pipelines, SQL/Python, automation, data governance through controls). But this role is specifically Azure-native (ADF/Synapse/ADLS/Databricks) and expects hands-on Azure Data DevOps and modeling practices, which are not evidenced. **Strengths:** Strong data quality/control mindset, SQL and analytics orientation, Automation-first approach to operational problems **Critical Gaps:** Hands-on Azure data ecosystem (ADF/Synapse/ADLS/Databricks) not demonstrated **Inferred Skills:** Data governance via validation/field locks, Data quality remediation and prevention, Schema reasoning and data modeling **Missing Required:** ADF experience, Synapse/ADLS experience, Azure data platform management and optimization, Data DevOps practices (explicit) **Missing Nice-to-Have:** Power BI, DP-203 certification, Formal data governance program experience (explicit)

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.2] There is partial relevance through Python/SQL, automation, and building systems that run reliably with low maintenance. But this is a principal-level data platform infrastructure role requiring deep cloud/IaC/CI-CD/data warehouse administration and enterprise-scale platform engineering experience not reflected in the resume. **Strengths:** Building maintainable automated systems, Strong SQL/data reasoning, Clear stakeholder communication and ownership **Critical Gaps:** Principal-level data platform infrastructure + IaC/CI/CD not demonstrated **Inferred Skills:** Data pipeline design thinking, Operational tooling and process improvement, SQL-based analysis and performance awareness (light) **Missing Required:** 10+ years infrastructure/data platform/big data engineering, IaC design and hands-on, Cloud services depth (AWS/GCP), Data warehouse administration experience **Missing Nice-to-Have:** Airflow/dbt, Kubernetes, TDD

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] The candidate brings Python/SQL skills and ETL-like experience, but lacks concrete exposure to GCP tools (BigQuery, Dataflow, Composer) and DBT, which are central to the role. Their background is more in operational automation than cloud-native big data engineering. **Strengths:** Solid data intuition from supply chain and finance experience, Proven ability to automate operational processes instead of relying on manual data work, Comfort collaborating with multidisciplinary teams **Critical Gaps:** No concrete background running production data pipelines in GCP or equivalent cloud data platforms **Inferred Skills:** SQL and Python for data processing, Data integrations via APIs and ERPs, Experience supporting analytics and automation through reliable data **Missing Required:** Experience with cloud data tooling such as BigQuery, Dataflow and Composer, DBT-based transformation pipelines, Experience integrating multiple enterprise databases into unified cloud data flows **Missing Nice-to-Have:** Experience with Apache Airflow, GCP Dataflow and IBM InfoSphere DataStage

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] Although the candidate has Python/SQL and platform-thinking experience, this position demands deep hands-on AWS data platform expertise (Athena, SageMaker, Airflow, Glue, QuickSight, Lake Formation, IAM, FinOps) that is not visible in the profile. Their cloud exposure is described only as foundational. **Strengths:** Good understanding of data consumers’ needs and reporting requirements, Experience managing cost and stability in business operations (even if not in cloud), Ability to contribute to platform governance and process improvements **Critical Gaps:** No proven experience running or evolving a complex AWS-based data platform at scale **Inferred Skills:** Python automation and scripting, SQL optimization for operational reporting, Governance mindset from implementing validation rules and field-level controls **Missing Required:** Hands-on AWS experience with key analytics and orchestration services (Athena, SageMaker, Glue, Airflow, QuickSight), Python automation for platform components in AWS, Strong SQL performance tuning for analytical workloads **Missing Nice-to-Have:** DevOps and CI/CD tooling experience, Experience with MLOps pipelines on AWS, Experience with EKS, VPC design and Security Groups, Prior experience as a data engineer in financial institutions

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] This role is heavily focused on AWS-based data platforms, infrastructure as code (Terraform/CDK), Airflow, Snowflake, dbt and streaming (Kafka/Kinesis), which the candidate does not show. Their strengths lie in systems automation and AI/LLM tooling rather than in large-scale AWS data platform engineering. **Strengths:** Strategic mindset about data and automation as infrastructure, Experience mentoring and aligning with business stakeholders, Ability to balance long-term vision with short-term impact in systems design **Critical Gaps:** No demonstrated experience designing and operating a large-scale AWS data platform with infrastructure as code and streaming **Inferred Skills:** Python scripting for automation, Experience designing autonomous, reliable operational systems, Basic AWS understanding and strong interest in AI/ML products **Missing Required:** 5+ years specifically in data/platform/infra engineering, Proven design and maintenance of AWS data platforms (ECS, EMR, Lambda, Step Functions), Experience with Terraform or CDK for infrastructure automation, Experience with Airflow, Snowflake and dbt **Missing Nice-to-Have:** MLOps stack experience (feature store, model registry, serving), LLM infrastructure exposure beyond high-level integrations

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5.1] Strong alignment on backend development with Node.js/Python and practical GenAI integration, matching the core of this AI backend specialist role. Gaps are mainly around NoSQL, CI/CD, observability and explicit vector stores/agent frameworks rather than in the fundamental domain. **Strengths:** Strong overlap with backend + IA Generativa integration requirements, Proven ability to design reliable, low-touch systems in production contexts, Good understanding of APIs, integrations and governance around AI usage **Inferred Skills:** Backend API development using Node.js and Python, GenAI integration and prompt engineering based on LLM tooling and self-hosted clusters, Data modeling and validation for critical operational systems, Experience running production-like automated services with minimal manual intervention **Missing Required:** Experience with NoSQL databases in production (e.g., MongoDB, Redis), Documented CI/CD and test automation practices for backend services, Experience integrating vector stores for context retrieval, Hands-on development of AI agents integrated into products **Missing Nice-to-Have:** Deep experience with at least one major cloud provider (AWS, GCP, Azure), Operational observability stack (metrics, logging, tracing)