Anti-ATS Evaluatorv1.3

[ANALYSIS_REPORT] **LOW** [gemini-3.1-pro-preview] While the candidate has finance experience and strong Python/SQL skills, this role heavily emphasizes big data tooling like PySpark and Hadoop. The candidate works mostly with Postgres, SQLite, and custom Go implementations. Adapting the resume is not feasible without hands-on Spark experience. **Strengths:** Python ETL, SQL, Financial sector knowledge **Critical Gaps:** Big Data ecosystems **Missing Required:** Apache Spark

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Hard geographic requirement (presencial em Belém) conflicts with candidate location; ATS will auto-filter. Candidate has relevant Python/SQL and pipeline experience but lacks explicit GCP production experience listed in the JD. To improve: state willingness to relocate or remote/onsite flexibility and add GCP projects/certification. **Strengths:** Python-based pipelines, SQL/Postgres experience, Production scraper & orchestration **Critical Gaps:** On-site in Belém requirement (geographic) **Missing Required:** Disponibilidade para trabalho presencial em Belém

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Strong Python and SQL usage and clear end-to-end pipeline experience raise the ATS base, and the candidate’s custom orchestrator demonstrates orchestration skills. Missing explicit Spark experience (required) reduces score and triggers a missing_required cap. Improve by adding Spark experience, example ETL using Spark, or CI orchestration examples. **Strengths:** End-to-end pipelines in production, Python + SQL applied at scale, Custom orchestrator and reliability engineering **Missing Required:** Domínio de Spark (required)

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Candidate meets the seniority and developer-experience thresholds (multiple production projects, 12+ years) and shows solid data pipeline, quality and ingestion experience plus English fluency. Strong match on practical ETL/quality responsibilities and production readiness. Improve by calling out explicit years doing data engineering and adding short case studies of data quality monitoring. **Strengths:** Production ETL/ELT and data quality, Python + SQL + pipelines, Portfolio of deployed systems and English C2

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT4.1] Strong LLM, AI workflow, and automation experience. Lacks explicit EdTech experience and no SE title, but meets most technical requirements. To improve, highlight any educational content or EdTech-related projects. **Strengths:** LLM integration, AI workflow design, Automation

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT4.1] Strong Postgres, SQL, and automation experience. Lacks direct MySQL, Redshift, dbt, AWS DMS, and deep data warehousing at scale. No explicit experience with streaming tech or fintech. To improve, highlight any MySQL/Redshift exposure and clarify scale of data systems. **Strengths:** Postgres, SQL, Data architecture

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Strong LLM/RAG and pipeline experience give relevant ML/AI coverage but candidate lacks explicit deep-learning framework (PyTorch/TensorFlow) and several named MLOps tools, reducing ATS score. Demonstrated production pipelines and MLOps-thinking partially compensate via inferred skills. To improve: add PyTorch/TensorFlow projects, list ML lifecycle tools (Airflow/MLflow/DVC) and concrete MLOps responsibilities. **Strengths:** LLM/RAG and prompt/pipeline experience, Production deployment and inference design, Data pipeline & orchestration background

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Candidate shows strong pipeline, orchestration and SQL skills but lacks explicit expertise with the AWS streaming ecosystem (Kinesis/Lambda/Redshift) demanded by this senior role. Transferable systems and event-processing experience reduces the gap but ATS will flag missing AWS streaming keywords. Improve by adding AWS streaming experience or proof of similar real-time/event-driven architectures. **Strengths:** Event-batching and orchestration experience, SQL + production ETL expertise, Custom reliable orchestrator in production

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT4.1] Strong AI/ML, LLM, vector DB, and automation experience. Lacks explicit IDP/OCR/document classification and AWS certification. No direct evidence of deploying in regulated industries. To improve, highlight any document processing or regulated industry work. **Strengths:** LLM pipelines, Vector DBs, AI architecture

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] This Principal DB role demands deep Oracle/SQL Server, PL/SQL and a specific ETL/toolchain (ODI/GoldenGate/OBIEE) where the candidate’s PostgreSQL/modern stack experience doesn't match; this is a critical skills-domain mismatch. While strong in general data architecture, the specialized enterprise DB stack is a blocking gap. Recommend against applying unless the candidate has direct Oracle/SQL Server/ODI experience. **Strengths:** SQL expertise (Postgres), data modeling, architecture & ETL experience **Critical Gaps:** Specialized Oracle/SQL Server enterprise stack not present **Missing Required:** 6+ years in specific relational/Oracle/ETL tooling (per JD)

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Candidate’s experimental design, statistical background (trading/forecasting) and LLM/pipeline work align well with the role’s focus on metrics, ground truth, EDA and model evaluation. The mix of product-facing experiment discipline and automation is a strong match. Improve by documenting specific evaluation suites, regression tests and monitoring dashboards in the resume. **Strengths:** Experiment design & statistical rigour, Dataset/ground-truth construction and EDA, LLM/RAG evaluation and monitoring experience

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Strong alignment with LangChain/RAG/agentic AI and production RAG pipelines but JD requires 6+ years AI/ML experience which the ATS may treat as a hard seniority gap. Candidate’s hands-on LangChain/RAG and production LLM work offset years shortfall somewhat, producing a strong-but-capped score. Improve by clarifying duration of AI/ML work and showing leadership/mentorship examples. **Strengths:** LangChain/RAG production experience, LLM APIs, graph-RAG knowledge, agent architectures, Production-grade deployment experience **Missing Required:** 6+ years experience in AI/ML (JD)

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Candidate demonstrates solid data engineering, ETL and analytical capabilities but lacks domain-specific Legal Ops experience and explicit BI tool names (PowerBI/Tableau). Transferable skills (governance, LGPD awareness, pipelines) make this a reasonable match with minor gaps. Improve by adding examples of compliance-related work, LGPD handling, and any BI/dashboard projects. **Strengths:** Data pipeline design and data quality, Governance mindset and LGPD awareness, Experience with ETL and BI consumption patterns

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] The project is directly aligned with the candidate’s LLM, RAG, scraping/parsing and domain-integration experience; practical e-commerce/product work also matches the business-technical bridging requirement. Strong fit for delivering the corporate knowledge questionnaire automation. Improve by adding explicit examples of document parsing/QA pipelines and LGPD/privacy handling. **Strengths:** LLM/RAG + retrieval + QA pipelines, Web scraping and document parsing, Experience translating business needs into production solutions

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT4.1] Strong AI, automation, and systems experience. Lacks explicit evidence of deep AI research or large-scale AI deployments, but matches most requirements. To improve, highlight any large-scale AI project leadership. **Strengths:** AI solutions, Automation, Systems architecture

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Excellent alignment: candidate demonstrates end-to-end agent/LLM work, RAG, vector stores, orchestration, scraping and experiment pipelines that this remote IA engineer role asks for. Minor gaps (e.g., Snowflake mention) are not blocking given strong production experience. To improve, call out any vector-db/Snowflake integrations and MLOps/versioning work explicitly. **Strengths:** Agent/LLM architecture and RAG in production, Vector search + scraping + pipeline automation, Product-to-engineering translation and MLOps thinking

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Strong match for LLM & agents development: candidate lists LangGraph/LangChain-style tools, RAG pipelines, deploy/monitor experience and Python capability. No major required gaps visible, so ATS score is high. Improve by listing specific agent frameworks used and short links to demos/docs in the application. **Strengths:** LLM/Agents + RAG production experience, Python + API integration expertise, Experience with pipelines and deployment in cloud environments

[ANALYSIS_REPORT] **TOP** [Copilot: GPT4.1] Excellent match for agentic AI, RAG, and knowledge graph systems. Strong experience with LangChain, LLMs, and mentoring. No critical gaps. To improve, highlight any experience with LlamaIndex or DSPy if available. **Strengths:** Agentic AI, RAG, Mentoring

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT4.1] Strong automation, AI agent, and data pipeline experience. Lacks explicit CRM/MarTech stack exposure. To improve, highlight any CRM or GTM system integrations. **Strengths:** AI agents, Automation, Data pipelines

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Candidate has strong data pipeline and identity/ETL conceptual skills but lacks explicit GCP/BigQuery hands-on evidence requested for Martech CDP work. Transferable architecture and identity-graph thinking are positives but ATS will penalize missing GCP/BigQuery keywords. Improve by adding any BigQuery/Dataflow/CDP examples or a migration/PoC demonstrating GCP competence. **Strengths:** Data modeling and pipeline architecture, Identity-unification conceptual experience, SQL and governance mindset

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Very strong fit: candidate has e-commerce domain experience plus agent orchestration, prompt/guardrails design, and production-aware monitoring—exactly what the JD requests. Few missing items and strong product+engineering bridge make the resume attractive. Improve by highlighting LGPD compliance steps and explicit guardrails examples in the application. **Strengths:** E-commerce automation experience, Agentic AI / RAG / guardrails design, Production monitoring and cost/latency trade-off awareness

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Candidate’s automation, workflow tooling (n8n, Zapier), analytics and product-to-tech translation map well to RevOps responsibilities though explicit CRM platform experience is not shown. Transferable skills in automation and analytics explain a strong but not perfect ATS match. Improve by adding concrete CRM tool experience (HubSpot/Salesforce/Marketo) and conversion-focused metrics. **Strengths:** Workflow automation (n8n, Zapier), analytics and KPI-driven delivery, Experience designing multi-channel automation, LLM-assisted content/analysis to accelerate RevOps

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT4.1] Strong data integration and automation experience. Lacks direct Snowflake, Segment, and Braze exposure. No explicit MarTech or marketing automation experience. To improve, highlight any relevant MarTech or data pipeline work. **Strengths:** Data pipelines, Automation, Integration

[ANALYSIS_REPORT] **LOW** [2.5-Pro] The score is low due to a critical domain mismatch. The role requires deep expertise in CRM intelligence and marketing conversion funnels, which the candidate's experience in supply chain, finance, and systems infrastructure does not cover. To improve, the candidate would need to acquire and demonstrate experience with core CRM platforms and marketing automation concepts. **Strengths:** Data Analysis, Statistical Modeling Concepts, Automation **Critical Gaps:** CRM Domain Expertise **Missing Required:** CRM platform experience

[ANALYSIS_REPORT] **LOW** [2.5-Pro] The score is zero because the job posting is an affirmative action role specifically for women ('Afirmativa Para Mulheres'). The candidate is male, which constitutes a hard filter, making him ineligible to apply. No resume modification can overcome this requirement. **Critical Gaps:** Does not meet demographic requirement **Missing Required:** Candidate must be a woman