Anti-ATS Evaluatorv1.3

[ANALYSIS_REPORT] **LOW** [Opencode: opencode:kimi-k2.5] Generalist IT infrastructure role not aligned with specialized trajectory. Good on cost calculation and general infrastructure mindset. Missing traditional IT admin experience, networking, telecom. English C2 is strong advantage. **Strengths:** Cost optimization, Infrastructure design, English C2, Stakeholder communication

[ANALYSIS_REPORT] **LOW** [Opencode: opencode:kimi-k2.5] Duplicate of Job 5. Critical gap: Zero Azure experience. Missing Java, Spring Boot, Kafka, Angular. Only PostgreSQL matches. Geographic fit (São Paulo hybrid) is irrelevant given complete stack mismatch. **Strengths:** PostgreSQL, Located in São Paulo **Critical Gaps:** Azure cloud platform, Java ecosystem **Missing Required:** Azure services, Java/Spring Boot

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Starts neutral but lacks any SAP ecosystem experience (ABAP, BTP, CPI) which is central to this JD; candidate’s strengths in systems integration and architecture add relevance but cannot substitute the SAP domain gap. Improve by adding direct SAP project experience, certifications or clear migration/integration work with SAP or by partnering with SAP specialists and documenting those engagements. Emphasize any middleware/CPI-like integrations and measurable architecture decisions in the resume. **Strengths:** Systems/integration architecture, Enterprise-grade data validation & ERP experience (TOTVS), OAuth/OIDC and production orchestration **Critical Gaps:** SAP ecosystem expertise (ABAP/BTP/CPI) **Missing Required:** SAP experience (listed in requirements)

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Good alignment on solution architecture, API-first patterns (REST, OpenAPI), OAuth2 and integration concerns; candidate brings hands-on architecture, integrations and engineering-to-business translation. Main improvement is explicit Azure/DevOps experience and formal architecture framework artifacts (TOGAF/ADRs) — add concrete examples and cloud migrations in Azure to boost ATS match. Highlight diagrams, PSA/ADRs and governance artifacts in the resume/portfolio. **Strengths:** REST/OpenAPI and OAuth2 practical experience, Solution architecture and cross-functional governance, LLM/RAG and automation platform design

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Solid match on AI architectures, LLMs, RAG and integration patterns and clear experience with production-oriented orchestration and DBs (Postgres/SQLite); however, the JD expects deeper cloud (AWS) and orchestration (Kubernetes) expertise than currently demonstrated. Improving by documenting any cloud/AWS deployments, Kubernetes/helm/operator exposure, and production messaging/streaming projects will raise the ATS score. Emphasize scale numbers, orchestration patterns and any Kafka/RabbitMQ-like experience. **Strengths:** LLM/AI infra and RAG pipelines, Production orchestration and containerization (Docker), Postgres and performance-minded design **Missing Required:** Demonstrable AWS/Kubernetes production expertise

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] The candidate has strong Python, SQL/PostgreSQL, automation, and AI pipeline experience but lacks nearly all of the specific big data and ML engineering stack listed (Apache Beam/Spark, MLflow/Kubeflow/Vertex, Airflow/dbt/Airbyte, GCP/Azure). Enterprise ATS will heavily weight exact tool matches and libraries like pandas, Dask, Streamlit, which are not explicitly present in the resume, dragging the score down despite good general capability. To improve for this JD, the candidate would need to add concrete examples of Python data pipelines using pandas and visualization libraries, plus show any exposure to Spark-like distributed processing, Airflow/dbt-style orchestration, and cloud deployments (even at small scale). **Strengths:** Python-based automation and data processing in production, PostgreSQL and SQL database experience, AI/LLM pipeline design and scoring logic **Missing Required:** Apache Beam, Spark/PySpark production experience, MLflow or Kubeflow Pipelines and Vertex AI, Airflow/dbt/Airbyte or equivalent ETL orchestration in production, Deep hands-on experience in GCP and Azure, Kubernetes and Helm, Terraform and Azure DevOps, Explicit use of pandas for data manipulation

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Strong match for product-focused AI/ML roles: candidate shows end-to-end LLM pipeline design, prompt engineering, data pipeline governance and automation which align closely with the JD. To improve further, add explicit supervised model training/validation examples (frameworks, hyperparameter work, deployment & monitoring) and measurable production ML metrics. Include examples of evaluation/CI for models and governance processes to strengthen the ML engineering signal. **Strengths:** RAG and prompt engineering pipelines, Data pipeline design and governance, Operational automation and product-minded delivery

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] The candidate aligns well conceptually with MLOps and LLM evaluation ideas and has strong Python, CI/CD, and LLM API experience, but lacks nearly all of the concrete platform components listed (MLflow + Databricks, AWS EKS/Kubernetes, Terraform, observability stack). ATS will prioritize explicit matches on MLflow, Databricks, EKS, Terraform, and observability tools, which are absent, so inferred skills cannot fully compensate. To improve, the candidate should highlight any existing Kubernetes, Terraform, or MLflow work (even small-scale), add explicit details on monitoring/metrics dashboards, and frame the job intelligence platform as a model lifecycle system if that is accurate. **Strengths:** Python development of production systems, LLM API usage (OpenAI, Gemini) and prompt engineering, Design of evaluation-like scoring pipelines for AI outputs **Missing Required:** MLflow with model registration and deployment workflows, Databricks Unity Catalog integration, AWS EKS and Kubernetes cluster operations (including GPU scheduling), Terraform module authoring and state management, Production-grade observability across ML stack, Deep CI/CD for ML (GitHub Actions or similar) tied to model pipelines

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5.1] The candidate matches the Senior Staff Software Engineer role very well on systems architecture, automation mindset, AI integration, and Brazilian financial domain exposure (quantitative trading, financial analysis), with 12+ years of experience and founder-level ownership. There are no hard tool requirements, so ATS will see strong signals in systems design, AI strategy, and business-technical translation that align with defining target architecture and integrating AI into engineering. To further improve, the candidate should explicitly frame recent work in staff-like language (technical leadership, cross-team roadmaps, mentoring) and tie financial/automation achievements to platform-scale outcomes. **Strengths:** Systems architecture and constraint-based engineering, Financial and trading domain experience relevant to fintech, Proven ability to define and deliver complex automation platforms end-to-end

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] The candidate has good data-architecture instincts, SQL/database experience, and some ML/analytics exposure, but lacks the heavy big data and streaming stack this role centers on (Kafka/Nifi, Scala/Spark, Hadoop ecosystem, large cloud data platforms). ATS will heavily favor candidates listing Spark/Scala, Kafka, Data Lake/warehouse design at scale, and cloud deployments, which are not present in the resume. To raise fit, the candidate would need to show concrete experience with at least one major streaming platform (Kafka), one big data environment (Spark/Hadoop), and cloud-based data modeling/ETL in addition to current automation projects. **Strengths:** Strong SQL/PostgreSQL and data-quality remediation experience, Experience specifying validation rules and data governance at the ERP level, Solid analytics and forecasting background from supply chain and finance **Missing Required:** Scala and/or Spark programming in production, Kafka or Nifi hands-on streaming experience, Mature ETL/ELT pipelines for Data Lake/Data Warehouse workloads, Production ML (MLP, RNN, CNN) beyond LLM/RAG usage

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5.1] The candidate aligns strongly with a Business AI Solutions Architect role through end-to-end AI product building (job intelligence platform), deep LLM experience (Claude, Gemini, OpenAI), and a clear business-technical bridge profile. They also have zero-to-one product delivery and startup experience, which maps well to forward-deployed, customer-embedded technical work. To optimize for ATS, the candidate should more explicitly emphasize experience with scalable web/enterprise stacks, working with executives, and any exposure to advertising, social media, or enterprise B2B environments. **Strengths:** End-to-end AI product development from scraping to orchestration to UI, Strong LLM and agentic thinking with multiple providers, Proven ability to translate business needs into concrete technical architectures

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5.1] The candidate is an excellent conceptual fit for an LLM/AI solutions architect in a B2B SaaS-like setting, with strong generative AI, RAG, and systems-architecture experience plus a clear record of acting as a business-technical bridge. However, the resume does not explicitly show prior Solution/Enterprise Architect roles in B2B SaaS or deep cloud platform ownership, which ATS will treat as missing core experience. Adding explicit framing of the current role as solution/enterprise architecture work, plus any concrete AWS/GCP architectural responsibilities, would significantly strengthen alignment. **Strengths:** Hands-on design of complex AI and LLM-based systems, Business-oriented communication and translation of technology into value, Experience leading automation and architecture decisions as a founder/head of engineering **Missing Required:** Proven experience as Solution Architect/Enterprise Architect in B2B SaaS environments, Deep hands-on cloud background with one major provider (AWS, GCP, or Azure) beyond fundamentals

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Strong in architecture and AI but the JD specifically calls for Java-centred architecture; candidate’s language stack (Go, Python, JS) and lack of explicit Java experience is a meaningful gap. To improve, add Java projects, migration/interop work, or code samples showing Java competency, or highlight architectural leadership over Java teams rather than hands-on Java if available. Emphasize any work integrating Java services or guiding Java teams in architecture docs/ADRs. **Strengths:** Architectural leadership and AI adoption, Go/Python production systems experience, Experience embedding AI into developer workflows **Missing Required:** Explicit Java experience (listed in requirements)

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5.1] The candidate brings solid systems architecture experience and AI-platform thinking, with cloud fundamentals and a strong constraint-based engineering approach, which align with a Staff System Architect for AI solutions. However, the resume does not show large-scale event-driven architectures on AWS/GCP or prior staff-architect roles coordinating global teams, which are central to this JD. To improve fit, the candidate should highlight any event-driven or message-based architectures, emphasize cloud design decisions (latency, HA, global traffic), and frame leadership work as cross-team architectural guidance. **Strengths:** Strong systems-design mindset and RTOS-inspired orchestration experience, AI architecture exposure from building an AI-centric job intelligence platform, Ability to act as technical reference and decision-maker as Head of Engineering **Missing Required:** Cloud-native event-driven architecture experience in AWS and GCP at significant scale, Previous staff-level or equivalent architectural leadership across multiple teams

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5.1] This role is highly aligned: the candidate has strong Node.js/Python backend experience, LLM/RAG pipeline expertise (LangChain, embeddings, vector search), and architectural leadership as Head of Engineering, all in Brazil with native Portuguese and C2 English. The only notable gaps are around explicit multiagent customer-service implementations at large scale and named tools like LangGraph/Semantic Kernel, which are adjacent to the candidate’s current stack. To further optimize, the candidate should explicitly describe any multiagent or orchestrated-agent patterns used in current systems and add specific LangChain-based workflows and telemetry/monitoring strategies. **Strengths:** Deep practical experience with LLMs, RAG, embeddings, and vector similarity search, Node.js and Python backend skills applied to real production systems, Proven architectural and people leadership in an AI-heavy, automation-focused context

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] This role explicitly requires a PhD in a technical/scientific field or an MSc plus at least two years of ML-focused experience, which the candidate does not have on paper. While the candidate has strong analytical and engineering skills, lack of formal advanced degrees and healthcare ML domain experience will cause most enterprise ATS systems to auto-filter the application. Even with a human review, the absence of healthcare data and deep supervised ML tooling (XGBoost, PyTorch/TensorFlow, etc.) would be a major obstacle. **Strengths:** Strong quantitative background and statistical thinking from trading and supply chain, Experience building automated pipelines and data-driven systems, Excellent communication and cross-functional collaboration history **Missing Required:** PhD in a technical/scientific area OR MSc plus at least two years ML-focused experience, Practical experience with supervised ML methods like XGBoost and deep learning, History of working in large collaborative ML codebases with TDD, CI/CD, and MLOps

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT4.1] The candidate demonstrates strong Python, data pipeline, and AI system architecture skills, with hands-on production deployments and experience with LLMs. However, there is no explicit evidence of deep TensorFlow/PyTorch/scikit-learn usage, MLflow/MLOps, or a Master's degree, and no direct mention of mentoring or technical leadership in ML teams. To improve, the candidate should highlight concrete ML model training/deployment with these frameworks and clarify any advanced academic credentials. **Strengths:** Python production systems, AI/LLM integration, Data pipeline architecture **Missing Required:** Master's degree in CS/Stats/Math or related

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT4.1] The candidate has extensive automation, integration, and RPA experience, with a proven track record of building and maintaining automated business processes. While there is no explicit mention of RPA-specific tools, the skillset and project history strongly infer the required capabilities. To further strengthen the match, the candidate could mention direct experience with RPA platforms or frameworks. **Strengths:** Automation systems, API integration, Production ops

[ANALYSIS_REPORT] **LOW** [Copilot: GPT4.1] The candidate has strong SQL, data architecture, and automation experience, but lacks direct Informatica IICS, MS SSIS, Power BI, and Azure Data Services expertise. The resume does not show 5-7 years of BI application development or deep cloud platform experience. To improve, the candidate should highlight any relevant BI, ETL, or Azure experience and address the specific tool gaps. **Strengths:** SQL/data modeling, Process automation, Data validation **Missing Required:** 5-7 years BI application development, Informatica IICS

[ANALYSIS_REPORT] **TOP** [Copilot: GPT4.1] The candidate has strong experience with API integrations, automation, n8n, LLMs, and both backend and frontend development using relevant stacks. There is no explicit mention of Blip or MongoDB, but adjacent experience with similar platforms and databases is present. To maximize fit, the candidate could mention direct experience with messaging platforms and MongoDB. **Strengths:** API integration, n8n automation, LLM/AI integration

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Relevant chatbot and LLM experience (Node.js, Puppeteer, prompt engineering) but the JD requires proven experience with the Blip platform which is not present on the resume. Improve by adding direct Blip projects or demonstrating quick platform transferability (docs, small porting examples) and by highlighting conversational UX/metrics and channel integrations (WhatsApp, FB). Adding a short portfolio example of a chatbot with measured KPIs would raise ATS and human interest. **Strengths:** LLM/chatbot design and integration experience, Node.js/JavaScript and API integration skills, Experience with channels and automation (WhatsApp integration, webhooks) **Missing Required:** Blip-specific development experience (listed)

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT4.1] The candidate has strong AI/ML, full-stack, and production deployment experience, but lacks a four-year CS degree and explicit experience with Cursor, OpenCode, Aider, Void, and evaluation frameworks like Langfuse. The resume demonstrates 0-to-1 product delivery and LLM integration, but not all required frameworks are covered. To improve, the candidate should clarify degree equivalence and highlight any experience with the listed AI agent tools. **Strengths:** AI/ML production systems, Full-stack delivery, LLM integration **Missing Required:** Four-year college degree (CS or equivalent)

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT4.1] The candidate has strong data architecture, validation, and governance experience, with a proven track record in ERP and master data management. However, there is no explicit mention of MDM tools or large-scale enterprise data flows. To improve, the candidate should highlight any direct MDM or large-scale data integration experience. **Strengths:** Data validation, ERP integration, Governance practices

[ANALYSIS_REPORT] **TOP** [Copilot: GPT4.1] The candidate matches all required skills, including Python, Node.js, APIs, microservices, automation, and both frontend and backend development. There is adjacent experience with Docker, cloud, and CI/CD, and strong automation and integration history. To further strengthen the application, the candidate could mention direct experience with preferred tools like Kubernetes and messaging platforms. **Strengths:** Python/Node.js, Automation, Full-stack development

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Excellent match — resume explicitly lists n8n, automation workflows, JavaScript, SQL and OAuth/webhook integrations, matching the JD closely with production examples. Minor improvements would be to call out SUPABASE or exact CRM integrations (RD Station, PipeRun) by name and add measurable performance/uptime metrics for flows. Highlighting a few named CRM integrations and a public n8n workflow in the portfolio will further improve conversion. **Strengths:** Direct n8n experience, APIs/webhooks/OAuth proficiency, Practical automation + monitoring and production hardening