Anti-ATS Evaluatorv1.3

[ANALYSIS_REPORT] **MEDIUM** [2.5-Pro] The candidate scores reasonably well due to strong, demonstrated skills in building data pipelines and integrating AI, which are core to this Data Engineer role. However, the score is capped by a lack of specific experience with MarTech/AdTech tools, a required domain knowledge. To improve, the person should tailor his resume to emphasize the ETL aspects of his projects and perhaps take a short course on the MarTech data ecosystem to speak the language. **Strengths:** Data Pipelines, AI Integration, Systems Architecture **Missing Required:** Experience with marketing/advertising data sources

[ANALYSIS_REPORT] **TOP** [2.5-Pro] The candidate is an exceptionally strong match, with his recent project directly demonstrating the core requirements: building production-ready AI solutions, including RAG and autonomous agent/orchestration systems. The score is near-perfect because his hands-on experience developing a full platform aligns perfectly with the JD's focus on practical, end-to-end AI engineering. The only minor weakness from an ATS perspective is the lack of a formal 'Software Engineer' title. **Strengths:** Production AI Systems, RAG Implementation, System Orchestration (Agentic Systems)

[ANALYSIS_REPORT] **TOP** [Copilot: GPT4.1] Excellent match for AI agent deployment, customer-facing problem solving, and end-to-end delivery. Strong systems and automation background. No critical gaps. **Strengths:** AI agents, Customer solutions, End-to-end delivery

[ANALYSIS_REPORT] **LOW** [Copilot: GPT4.1] Strong JavaScript and SQL experience, but lacks explicit web A/B testing, HTML/CSS, and Google Analytics exposure. No direct marketing or CRO experience. To improve, highlight any web experimentation or optimization work. **Strengths:** JavaScript, SQL, Web development

[ANALYSIS_REPORT] **LOW** [2.5-Pro] The score is extremely low because this is a highly specialized role requiring senior-level expertise in the Salesforce Marketing Cloud ecosystem. The candidate's resume shows no experience with Salesforce, Marketing Cloud, or related tools like BigQuery, which are all critical requirements. His general data skills are not transferable enough to overcome such a large, platform-specific knowledge gap. **Critical Gaps:** Salesforce Platform Expertise **Missing Required:** Salesforce Marketing Cloud, ETL for Salesforce

[ANALYSIS_REPORT] **LOW** [Copilot: GPT4.1] Strong AI and automation experience, but lacks direct Salesforce, Agentforce, and SDLC/consulting experience. No evidence of Salesforce certifications or customer discovery workshops. To improve, gain hands-on with Salesforce and related tools. **Strengths:** AI-driven solutions, Automation, Technical translation

[ANALYSIS_REPORT] **HIGH** [2.5-Pro] The candidate is a strong fit for the core responsibilities, demonstrating deep, practical knowledge in creating AI agents, orchestrating LLMs, and building the necessary pipelines—all key requirements. The score is reduced slightly due to a lack of experience with the specific enterprise platforms mentioned (Copilot Studio, Power Platform, Databricks). However, his foundational skills are strong enough that he could learn these tools quickly. **Strengths:** AI Agent Architecture, LLM Orchestration, API & Pipeline Automation

[ANALYSIS_REPORT] **LOW** [Copilot: GPT4.1] Strong AI and automation experience, but lacks direct Copilot (Microsoft 365/GitHub) and governance experience. No evidence of prompt engineering for Copilot or LLM governance frameworks. To improve, gain hands-on with Copilot and related governance work. **Strengths:** AI solutions, Automation, Mentoring

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Strong hands‑on LLM/API experience, OAuth/SSO, backend (Node/Python) and engineering of production pipelines match core JD requirements. Missing explicit Kubernetes and observability/KPI telemetry experience caused deductions. To improve: add explicit k8s, Prometheus/Grafana, and structured logging examples in the resume and call out multi-tenant/versioning work. **Strengths:** LLM APIs & RAG pipelines, OAuth/OIDC & SSO implementation, Backend production systems (Go/Python/Node) **Missing Required:** Kubernetes, Observability

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.2] Candidate has Python plus real production LLM pipeline experience, but the JD is for traditional ML engineering with Spark and large-scale ML applications plus 5+ years ML. ATS will treat "LLM scoring pipeline" as adjacent, not equivalent to feature engineering/training/retraining pipelines at scale. Improve by adding any real Spark/PySpark work, model training/retraining examples (metrics, datasets, deployment), and explicitly labeling ML lifecycle ownership. **Strengths:** Python, production automation systems, LLM/prompt pipeline design **Missing Required:** Spark, 5+ years Machine Learning experience, large-scale ML applications

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Direct experience with RAG, embeddings and LLM pipelines aligns with JD needs, and candidate shows practical pipeline builds. Missing the explicitly requested CS/comp-sci degree and deep Azure specialization reduces ATS relevance. Improve chances by surfacing equivalent formal training and Azure experience (certs/projects) or noting degree-equivalent coursework. **Strengths:** RAG & embedding pipelines, Practical LLM API integration, Production ETL/scraping and validation logic **Missing Required:** Formação em Ciência da Computação (explicit in JD)

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Same JD as 4383282310: strong RAG and embedding experience, but lacks explicit CS degree and deep Azure experience requested. Candidate's applied projects are relevant but the degree requirement will be treated strictly by ATS. Improve by documenting equivalent formal coursework/certificates and Azure projects. **Strengths:** RAG & embedding pipelines, LLM API integrations, Production data pipelines **Missing Required:** Formação em Ciência da Computação (explicit in JD)

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Candidate shows solid Python/SQL and smaller-scale pipeline work plus ERP data cleansing — relevant to data engineering tasks. Missing explicit large-scale Big Data tech (Hadoop/Spark/Kafka) and deeper cloud experience caused notable deductions. Improve by highlighting any distributed processing, Spark exposure, and cloud data tools or by completing short projects/PRs using Spark/Kafka. **Strengths:** Python ETL & data pipelines, Strong data validation and governance experience, Postgres/SQL proficiency **Missing Required:** Hadoop/Spark/Kafka (listed in JD)

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5.2] Candidate strongly matches LLM APIs (OpenAI/Claude/Gemini), prompt engineering, SQL, CI/CD, and shipping production systems, which ATS will score well. Gaps are explicit FastAPI/Flask API experience, voice platforms (Vapi/Retell/Twilio), MongoDB/NoSQL, and the stated 5+ years professional software development expectation. Improve by reframing 2020–present work as "software development" with concrete shipped artifacts (APIs, latency, uptime), and adding one small public FastAPI service + MongoDB example. **Strengths:** production LLM integrations, prompt engineering/model behavior iteration, SQL + backend systems mindset **Missing Required:** 5+ years professional software development experience (clearly evidenced), Python FastAPI/Flask in production, NoSQL/MongoDB, AI voice platforms (Vapi/Retell/Twilio)

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Job requires deep C#/.NET, SQL Server and Azure platform expertise; candidate primarily uses Go/Python and PostgreSQL, not .NET or SQL Server. Missing core language/framework (C#/.NET) is a critical gap causing heavy deductions. Not recommended unless candidate can demonstrate equivalent .NET experience or a fast-track conversion project. **Strengths:** LLM/AI integration experience, Backend systems and cloud fundamentals **Critical Gaps:** C# / .NET required (no evidence) **Missing Required:** C#/.NET (explicit)

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Solid foundation: Python, SQL, Postgres, Linux and experience automating production pipelines align with many data-engineering responsibilities. Major deductions for missing PySpark/Athena and deep AWS managed DB administration reduce the match. To improve, add concrete examples of PySpark jobs, RDS/Aurora administration, and cost/performance optimizations in cloud. **Strengths:** Python ETL & pipeline design, Postgres and SQL proficiency, Linux and automation experience **Missing Required:** PySpark/Athena (explicit in JD)

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Strong match: candidate has designed data ingestion pipelines, connectors, RAG/vector workflows, embeddings and production ETL — core JD areas. Minor gaps in dbt and explicit Azure/Data Lakehouse tooling caused small deductions. Improve by adding dbt/transform examples and explicit cloud Data Lakehouse experience. **Strengths:** RAG & vector store integration, End-to-end ingestion and ETL experience, Data modeling, governance and pipeline observability thinking

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Candidate demonstrates advanced Python/SQL skills and practical vector/RAG experience suitable for PoC/MVP work. Missing explicit ML framework (TensorFlow/PyTorch) projects and specific vector DB (Pinecone) caused deductions. Add concise examples of TF/PyTorch experiments and any Pinecone or vector-store projects to strengthen fit. **Strengths:** Advanced Python + prompt engineering, Experience building PoCs and production pipelines, Vector embeddings & RAG experience

[ANALYSIS_REPORT] **LOW** [Opencode: opus-4-6] Candidate has Python, SQL, and API pipeline construction experience which are required, and demonstrated strong data quality/ETL-adjacent work (ERP data sanitation, data pipelines). However, the JD requires deep MongoDB expertise (title-level requirement), Databricks, PySpark, Azure Cloud, and DevOps — none of which appear on the resume with demonstrated depth. The critical gap is MongoDB as a core required skill and Databricks/PySpark for Big Data processing. To improve: add any MongoDB/NoSQL project experience, highlight data pipeline work more explicitly with ETL terminology, and mention any Spark or distributed data processing exposure. **Strengths:** Python and SQL proficiency, API pipeline construction experience, Strong data quality and ETL-adjacent background (ERP data sanitation of 4000+ records) **Critical Gaps:** MongoDB (title-level requirement, zero demonstrated experience), Databricks/PySpark (Big Data processing stack) **Missing Required:** MongoDB, Databricks, PySpark, Azure Cloud

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.2] Candidate matches Python + LangChain/LLM application building and has strong DB fundamentals, but the JD is specifically anchored on Vertex AI + Terraform + agentic frameworks and managed vector search options. ATS will treat Google/Vertex as a hard specificity and mark it missing. Improve by adding any GCP/Vertex hands-on project (even a small demo) and explicitly listing Terraform/IaC usage plus vector DB (pgvector/Vertex Vector Search) work. **Strengths:** LangChain + embeddings concepts, production backend delivery, PostgreSQL/SQL **Missing Required:** Vertex AI, Terraform, Agentic frameworks (LangGraph/CrewAI)

[ANALYSIS_REPORT] **MEDIUM** [Opencode: opus-4-6] Strong alignment on Python, SQL, JavaScript, data pipelines, API integration, orchestration (custom Go orchestrator demonstrates deep understanding), prompt engineering, and AI integration via Claude/Gemini/OpenAI APIs. Candidate built vector search and RAG systems, matching the vector database requirement conceptually, though Pinecone specifically is missing. The critical gap is TensorFlow/PyTorch — the JD explicitly requires ML framework experience, and candidate has no demonstrated ML model training. To improve: highlight any ML experimentation even if informal, emphasize the orchestration and workflow automation depth, and explicitly mention vector store experience with embeddings listed on resume. **Strengths:** Python + SQL + JavaScript trifecta present, Production AI pipeline with Claude/Gemini/OpenAI API integration, Complex workflow orchestration and API/webhook architecture **Critical Gaps:** TensorFlow/PyTorch (ML frameworks explicitly required) **Missing Required:** TensorFlow or PyTorch

[ANALYSIS_REPORT] **LOW** [Opencode: opus-4-6] Candidate has RAG experience (listed in skills), API integration, financial sector background (Atlas Quantum, trading), and AI pipeline work. However, the JD demands advanced RAG variants (Self-RAG, CRAG, Auto-RAG) which are highly specialized, consolidated vector DB experience (Pinecone/Weaviate/Milvus), advanced Azure Cloud knowledge including Azure Functions and Cognitive Services, and a CS/Math degree (Mechatronics may not pass ATS filter for 'Ciência da Computação'). The critical gap is Azure expertise at the advanced level required. To improve: detail RAG implementation specifics in portfolio, mention any Azure exposure, and emphasize financial sector experience prominently. **Strengths:** Financial sector experience (Atlas Quantum, trading algorithms), RAG and embedding models listed in skills, API creation and integration experience **Critical Gaps:** Advanced Azure Cloud (deploy, Functions, Cognitive Services — completely absent), Advanced RAG variants (Self-RAG, CRAG, Auto-RAG — specialized knowledge not demonstrated) **Missing Required:** Azure Cloud advanced, Specific vector database experience (Pinecone/Weaviate/Milvus), Self-RAG/CRAG/Auto-RAG

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.2] This role requires deep Salesforce/Agentforce implementation plus specific Salesforce certifications; the resume does not show Salesforce platform delivery. ATS will auto-reject when mandatory certifications and Apex/LWC experience are absent. Improve only by applying after obtaining the relevant certs and demonstrating real Salesforce project work. **Strengths:** technical translation, data governance/quality thinking, LLM integration concepts (general) **Critical Gaps:** Salesforce platform implementation expertise **Missing Required:** Salesforce certifications (Advanced Admin/Service Cloud/Data Cloud/Agentforce/Sales Cloud), Salesforce/Agentforce hands-on experience

[ANALYSIS_REPORT] **MEDIUM** [Opencode: opus-4-6] Strong alignment: Node.js and Python backend (candidate built production Go+Node.js systems), CI/CD experience, Git/GitHub, AI Generativa integration via API (Claude/Gemini/OpenAI), Vector Stores and context retrieval (RAG, embeddings, vector search on resume), and agent development. Candidate's orchestrator project demonstrates distributed systems thinking and scalable service design. Missing pieces are specific observability tools (Prometheus/Grafana), NoSQL databases (MongoDB/Redis not demonstrated), and MCP/A2A protocols. AWS is listed as 'Fundamentos' which is light for cloud computing requirement. To improve: highlight the orchestrator as a distributed system with monitoring, mention any Redis/MongoDB usage, and explicitly reference the MCP protocol familiarity if any. **Strengths:** Production AI integration via multiple LLM APIs, Backend development in Node.js/Python/Go with scalable architecture, Vector Stores and RAG context retrieval techniques **Missing Required:** NoSQL databases (MongoDB/Redis), Observability tools (Prometheus/Grafana)

[ANALYSIS_REPORT] **LOW** [Opencode: opus-4-6] Candidate has Python, SQL, cloud fundamentals, English C2, and AI Generativa pipeline experience. However, the JD requires a 'Cientista de Dados Sênior' with proven experience across the full AI project lifecycle (preprocessing to production deployment), which implies ML model training, evaluation, and MLOps — areas where the candidate has no demonstrated experience. The role is through consulting firm Atos (mentioned in description), which is a red flag for culture fit. The 'Data Science' framing means ATS expects scikit-learn, pandas, model evaluation metrics, and statistical modeling experience beyond what the candidate demonstrates. To improve: emphasize any statistical analysis work from supply chain/trading, and highlight the AI pipeline lifecycle from the market intelligence platform. **Strengths:** Python and SQL proficiency, AI Generativa project experience, English C2 (advanced required) **Critical Gaps:** Data Science / ML model development (core role requirement, not demonstrated) **Missing Required:** Proven Data Science project lifecycle experience, ML model training/evaluation