Anti-ATS Evaluatorv1.3

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5.1] This JD is almost directly aligned with the Candidate’s recent work: LLM architectures, integration with ERPs and databases, automation of processes, Python/Node.js APIs and strong emphasis on security and code review. The only missing piece is explicit experience with MCP as a protocol, which is close to existing experience integrating LLMs with tools and data sources. To optimize fit, the Candidate should explicitly map prior ERP/LLM integration work to the MCP concept and emphasize security reviews and best practices in code handling and automation. **Strengths:** Extensive hands-on LLM and automation experience in production, Deep background integrating AI with ERPs, databases and business systems, Strong focus on code quality, security and review of AI-generated code

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5.1] The Candidate is very strong on Python, LangChain-style pipelines, RAG, multi-LLM usage and Docker, which aligns well with the core of this generative AI role. However, there is no explicit experience with Amazon Bedrock/AgentCore, LangGraph, Pydantic, Arize Phoenix, MCP or SSE/WebSocket streaming, which ATS will treat as important but partially adjacent. To improve, the resume should emphasize LangChain and RAG work in more detail, and any AWS/streaming experience, while potentially adding targeted projects involving Bedrock, Boto3 and streaming interfaces. **Strengths:** Strong practical experience building LLM pipelines and RAG systems, Expertise with multiple LLM providers and advanced prompt engineering techniques, Solid Python, Docker and systems design background including custom orchestrators **Missing Required:** Amazon Bedrock experience, LangGraph experience

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] This role combines ML automation with leadership of industrial automation projects involving PLC/SCADA, which are not present in the Candidate’s background. While the Candidate is very strong in Python, AI integration and API orchestration, ATS will see a critical gap around PLC/SCADA and industrial control systems experience. To truly fit, the resume would need concrete industrial automation projects with PLC/SCADA plus clearer MLOps tooling and cloud experience beyond fundamentals. **Strengths:** Strong Python and AI automation background suitable for ML integration work, Experience orchestrating complex API-based systems via custom schedulers/orchestrators, Systems thinking across operations, supply chain and engineering domains **Critical Gaps:** PLC/SCADA-based industrial automation experience **Missing Required:** Experience leading industrial automation projects with PLC/SCADA

[ANALYSIS_REPORT] **LOW** [Opencode: sonnet-4-5] ATS will struggle to match this resume to a credit risk modeling role. The candidate has strong statistical forecasting and data analysis experience (supply chain, trading strategies), and demonstrated ability to handle complex data problems (4,000+ corrupted records cleanup, demand forecasting). However, ATS will penalize the absence of 'Data Science' or 'Data Scientist' job titles, no direct credit risk modeling experience, and missing specific financial services domain keywords. To improve: add 'statistical modeling,' 'predictive analytics,' and 'risk assessment' explicitly to the resume where applicable (e.g., trading bot risk logic, demand forecasting models). **Strengths:** Statistical forecasting experience, Data quality and governance (4,000+ record cleanup), Complex data analysis (trading strategies, demand prediction) **Critical Gaps:** No Data Science job title, No credit risk domain experience **Missing Required:** Direct experience with credit risk models, Financial services background

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] The profile shows strong analytics, automation, and cross-functional translation skills, plus some finance and trading experience, which partially align with leading data-driven risk strategies. However, the JD requires a MSc/PhD in a quantitative field, a strong background in data science specifically for fraud detection/real-time decision systems, and experience in financial crime prevention, all of which are not evident in the resume. ATS will therefore see a partial skill match but a major domain and credential gap. **Strengths:** Strong background in building data-driven systems and monitoring strategy decay (trading and operational analytics), Proven ability to translate between business stakeholders and technical teams and own complex decision logic, Experience mentoring and leading initiatives in ambiguous environments through founder and consulting roles **Critical Gaps:** No direct fraud detection or financial crime prevention experience, which is core to this Risk & AI leadership role **Missing Required:** MSc or PhD in a quantitative field such as Computer Science, Engineering, Applied Math, Physics, or Statistics

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] While the candidate has quantitative and ML-flavored experience (trading strategies, AI scoring pipelines) and solid Python/SQL skills, the JD is highly specialized in Brazilian credit risk regulations, IFRS 9 modeling, and retail credit lifecycle, none of which are present. ATS will therefore detect strong general data and ML skills but a major mismatch in regulatory and credit domain expertise. This leads to a low but non-zero score driven mostly by transferable analytics skills rather than direct fit. **Strengths:** Strong programming skills in Python and SQL aligned with the technical stack, Experience designing ML-style strategies and monitoring performance decay over time, Ability to build and automate data-driven systems and reporting pipelines **Critical Gaps:** Lack of hands-on credit risk and retail banking domain experience, including retail credit lifecycle and payments/acquiring industry exposure **Missing Required:** Solid understanding of BACEN credit risk regulations such as Res. BCB 265/2022, CMN 4.557/2017, CMN 2.682/1999, and Circular 3.978/2020, Hands-on experience with IFRS 9 ECL modeling and provisioning methodologies, Practical experience across the retail credit lifecycle (origination, behavioral scoring, collection, and recovery), Experience in the payments and acquiring industry

[ANALYSIS_REPORT] **LOW** [Opencode: sonnet-4-5] This role requires deep ML/AI expertise with fraud detection, deep learning, and MLOps—areas where the candidate has conceptual knowledge but no production experience. ATS will detect Python, SQL, and general ML concepts, but will penalize missing Spark, MLOps pipelines, feature stores, and deep learning frameworks. The candidate's LLM API usage and prompt engineering don't translate to 'building ML models from scratch.' To improve: if the candidate has built any classification models (even simple ones for trading or inventory), explicitly frame them as 'predictive models' with performance metrics. **Strengths:** Python proficiency, SQL and data pipeline experience, Systems thinking for complex problems **Critical Gaps:** No ML engineering experience, No fraud detection domain, No deep learning production work **Missing Required:** Advanced Python + Spark + MLOps stack, Production ML model deployment, Fraud/risk modeling experience

[ANALYSIS_REPORT] **MEDIUM** [Opencode: sonnet-4-5] Strong fit for data governance due to hands-on ERP data quality work (4,000+ corrupted records, field-level validation rules, TOTVS schema reverse engineering). ATS will match SQL, Python, data quality concepts, and LGPD awareness. However, missing specific governance tooling (Databricks Unity Catalog, Collibra, Purview) and no formal 'Data Governance' job title will cap the score. The candidate's work is governance in practice but not in name. To improve: explicitly add 'data governance,' 'data quality framework,' 'metadata management,' and 'data lineage' to the resume where describing ERP cleanup and validation work. **Strengths:** Proven data quality expertise (4,000+ record cleanup), SQL + Python proficiency, LGPD awareness and data protection mindset **Missing Required:** Hands-on experience with enterprise data catalog tools

[ANALYSIS_REPORT] **MEDIUM** [Opencode: sonnet-4-5] Identical role to Job 3. Strong fit for data governance due to hands-on ERP data quality work (4,000+ corrupted records, field-level validation rules, TOTVS schema reverse engineering). ATS will match SQL, Python, data quality concepts, and LGPD awareness. However, missing specific governance tooling (Databricks Unity Catalog, Collibra, Purview) and no formal 'Data Governance' job title will cap the score. To improve: explicitly add 'data governance,' 'data quality framework,' 'metadata management,' and 'data lineage' to the resume where describing ERP cleanup and validation work. **Strengths:** Proven data quality expertise (4,000+ record cleanup), SQL + Python proficiency, LGPD awareness and data protection mindset **Missing Required:** Hands-on experience with enterprise data catalog tools

[ANALYSIS_REPORT] **HIGH** [Opencode: sonnet-4-5] Excellent alignment with the role's focus on AI architecture, GenAI/LLM implementation, RAG, and production integration. The candidate built a production LLM pipeline with prompt engineering, API integrations, OAuth/SSO, and custom orchestration—directly matching the JD. ATS will recognize Claude API, Gemini API, OpenAI SDK, RAG, embeddings, prompt engineering, Go, Python, PostgreSQL, CI/CD, and OAuth 2.0. Missing formal MLOps tooling and 'Arquiteto de Soluções' title will prevent a perfect score. To improve: add 'LLMOps,' 'AI governance,' 'guardrails,' and 'model monitoring' where applicable (e.g., prompt tuning variance reduction = quality monitoring). **Strengths:** Production GenAI/LLM pipeline (RAG, embeddings, prompt engineering), API integration expertise (Claude, Gemini, OpenAI), OAuth 2.0/OIDC implementation, Clean Architecture and systems design

[ANALYSIS_REPORT] **MEDIUM** [Opencode: sonnet-4-5] Identical role to Jobs 3 and 4. Strong fit for data governance due to hands-on ERP data quality work (4,000+ corrupted records, field-level validation rules, TOTVS schema reverse engineering). ATS will match SQL, Python, data quality concepts, and LGPD awareness. However, missing specific governance tooling (Databricks Unity Catalog, Collibra, Purview) and no formal 'Data Governance' job title will cap the score. To improve: explicitly add 'data governance,' 'data quality framework,' 'metadata management,' and 'data lineage' to the resume where describing ERP cleanup and validation work. **Strengths:** Proven data quality expertise (4,000+ record cleanup), SQL + Python proficiency, LGPD awareness and data protection mindset **Missing Required:** Hands-on experience with enterprise data catalog tools

[ANALYSIS_REPORT] **LOW** [Opencode: sonnet-4-5] This role focuses on Compliance risk modeling and automation, requiring statistical modeling and Databricks experience. The candidate has strong statistical forecasting (supply chain, trading), Python, SQL, and automation skills. However, ATS will penalize missing Databricks, no 'Data Scientist' title, and no Compliance domain experience. The automation and data extraction skills are transferable, but the lack of formal DS background and specific Databricks experience creates a gap. To improve: if using any cloud data platforms or big data workflows, mention them explicitly; frame demand forecasting and trading models as 'statistical models for risk assessment.' **Strengths:** Python and SQL proficiency, Automation mindset, Statistical analysis experience (forecasting, trading strategies) **Critical Gaps:** No 'Data Scientist' job title, No Databricks hands-on experience **Missing Required:** Databricks experience

[ANALYSIS_REPORT] **LOW** [Opencode: sonnet-4-5] This senior Data Scientist role requires credit/collection modeling, commercial propensity models, and GenAI/LLM experience. The candidate has GenAI production experience (LLM pipeline, RAG), Python, SQL, and business-to-technical translation skills. However, ATS will penalize missing PySpark, Databricks, and no direct credit or commercial modeling experience. The 'translate business challenges into analytical solutions' aligns perfectly with the candidate's strength, but the lack of 'Cientista de Dados' title and specific model types (scoring, behavior, propensity) creates a gap. To improve: frame trading strategies as 'propensity models' and demand forecasting as 'predictive scoring.' **Strengths:** GenAI/LLM production experience (strong differential), Python and SQL proficiency, Business-to-technical translation ability **Critical Gaps:** No 'Data Scientist' job title, No credit/collection domain experience **Missing Required:** Solid experience with credit models (Scoring, Behavior), PySpark or Databricks

[ANALYSIS_REPORT] **LOW** [Opencode: sonnet-4-5] This Microsoft security + AI governance consulting role requires deep Microsoft 365 security stack knowledge (Purview, Defender, Entra ID) and AI governance frameworks. The candidate has AI implementation experience (GenAI pipelines, OAuth/SSO, data security awareness), but ATS will penalize missing Microsoft ecosystem expertise, no security certifications, and no consulting background. English fluency is a strong match. The systems thinking and AI governance mindset align, but the lack of Microsoft-specific tooling and 'Consultor' title creates a gap. To improve: if familiar with any Microsoft tools or identity management concepts, mention them; frame OAuth 2.0 work as 'identity security.' **Strengths:** English fluency (C2), OAuth 2.0/OIDC implementation (identity security), AI governance mindset and data protection awareness **Critical Gaps:** No Microsoft ecosystem experience, No security consulting background **Missing Required:** Microsoft 365 security and governance experience, English (matched)

[ANALYSIS_REPORT] **LOW** [Opencode: sonnet-4-5] This Data Scientist III role (senior-level) requires advanced statistical modeling (Monte Carlo, sensitivity analysis), Databricks, and Compliance domain knowledge. The candidate has statistical forecasting experience, Python, SQL, and strong data quality skills, but ATS will penalize missing Databricks, no 'Data Scientist' title, and no Compliance background. The role's focus on anomaly detection and risk frameworks doesn't align with the candidate's automation/systems work. To improve: if the candidate has done any simulation work (even simple ones for inventory or trading risk), frame them as 'Monte Carlo simulations' or 'sensitivity analysis.' **Strengths:** Python and SQL proficiency, Statistical analysis background, Data pipeline and quality experience **Critical Gaps:** No 'Data Scientist' job title, No Databricks experience, No Compliance background **Missing Required:** Databricks hands-on experience

[ANALYSIS_REPORT] **MEDIUM** [Opencode: sonnet-4-5] This model validation role (fraud, AML, GenAI) requires statistical validation expertise and Databricks. The candidate has statistical analysis background, data quality rigor, and GenAI knowledge (production LLM pipeline), but ATS will penalize missing Databricks, no model validation experience, and no 'Analista de Riscos' title. The GenAI framework contribution aligns with the role's unique focus. Engineering background (Mechatronics) matches the 'Engenharias' requirement. To improve: frame data quality work (4,000+ record validation) as 'statistical validation testing' and prompt tuning variance reduction as 'model performance evaluation.' **Strengths:** GenAI production experience (framework contribution potential), Statistical inference background (forecasting, trading), Engineering degree (matches requirement), Data quality testing rigor **Missing Required:** Model validation or modeling experience, Databricks hands-on

[ANALYSIS_REPORT] **MEDIUM** [Opencode: sonnet-4-5] Identical role to Job 11. This model validation role (fraud, AML, GenAI) requires statistical validation expertise and Databricks. The candidate has statistical analysis background, data quality rigor, and GenAI knowledge (production LLM pipeline), but ATS will penalize missing Databricks, no model validation experience, and no 'Analista de Riscos' title. The GenAI framework contribution aligns with the role's unique focus. Engineering background (Mechatronics) matches the 'Engenharias' requirement. To improve: frame data quality work (4,000+ record validation) as 'statistical validation testing' and prompt tuning variance reduction as 'model performance evaluation.' **Strengths:** GenAI production experience (framework contribution potential), Statistical inference background (forecasting, trading), Engineering degree (matches requirement), Data quality testing rigor **Missing Required:** Model validation or modeling experience, Databricks hands-on

[ANALYSIS_REPORT] **LOW** [Opencode: sonnet-4-5] This senior Model Risk Analyst role requires deep expertise in model validation, governance, and regulatory compliance (Basel, IFRS 9). The candidate has statistical analysis background, data governance experience (ERP validation rules, data quality), and understanding of model risk concepts from trading strategies, but ATS will penalize missing 'Analista de Riscos' title, no formal model validation experience, and no regulatory framework knowledge. The governance and process documentation skills align well. To improve: frame ERP data quality work as 'model governance' and 'validation framework' implementation. **Strengths:** Data governance and quality enforcement, Process documentation and procedure design, Statistical analysis foundation **Critical Gaps:** No model risk management experience, No regulatory framework knowledge **Missing Required:** Model validation, monitoring, and governance experience

[ANALYSIS_REPORT] **MEDIUM** [Opencode: sonnet-4-5] Strong alignment for Unity Catalog governance role due to hands-on data governance work (ERP validation rules, data quality, schema design) and technical documentation skills. ATS will match SQL, Python, data governance concepts, and LGPD. The candidate's obsession with documentation ('Documentação será um pilar central' matches the JD's emphasis) and systems architecture mindset fit well. However, missing Databricks/Unity Catalog hands-on and no formal 'Governança' title will prevent top score. To improve: explicitly add 'data catalog,' 'data lineage,' 'access control policies,' and 'Unity Catalog' (if willing to learn quickly) to resume. **Strengths:** Data governance practice (ERP validation, access controls, quality rules), Technical documentation expertise, SQL and Python proficiency, LGPD compliance awareness **Missing Required:** Databricks and Unity Catalog configuration experience

[ANALYSIS_REPORT] **HIGH** [Opencode: sonnet-4-5] Good fit for AI Governance + Portfolio Management role due to systems thinking, cross-functional coordination (business/risk/tech), and GenAI production experience. ATS will match AI/ML conceptual knowledge, Python, SQL, and stakeholder management. The candidate's trajectory (Finance → Supply Chain → Systems → AI) demonstrates the ability to 'navigate between business, risk, technology, and architecture.' The GenAI production work (LLM pipeline, governance mindset) aligns with the pilot systems and risk assessment focus. Missing formal product/portfolio management experience and no 'Analista de Governança' title will cap score. To improve: frame weekly governance meetings and KPI reporting as 'portfolio management' and 'value tracking.' **Strengths:** GenAI/ML production experience with governance mindset, Cross-functional stakeholder coordination (business/tech/risk), Python + SQL proficiency, Systems thinking and value-driven approach

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5.1] The resume shows strong experience designing and validating quantitative-like models (trading strategies, AI scoring), with solid Python/SQL skills and an analytical mindset, which partially align with model risk review. However, the JD focuses specifically on Expected Credit Loss, PD/EAD/LGD models, BACEN 4966, IFRS9, ICAAP, and formal model risk management in a regulated banking context, none of which appear in the profile. ATS will thus treat this as a general DS/ML match with a major gap in credit risk and regulatory experience. **Strengths:** Experience designing, monitoring, and adjusting quantitative strategies and AI scoring pipelines, Strong Python and SQL programming abilities and comfort with Git-based workflows, Fast learner with demonstrated ability to understand complex systems and regulations (e.g., reverse-engineering ERP schemas) **Critical Gaps:** No direct experience with credit provision and capital requirement models, which are central to the role's mandate **Missing Required:** Experience with regulations and accounting standards such as BACEN 4966, IFRS9, and ICAAP specifically for credit provisions and capital, Direct experience developing or validating quantitative or machine learning models focused on credit provisions and capital requirements

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Score low because the JD requires deep Simatic Step 7 / PLC programming and an active CREA which are not present on the resume; candidate's mechatronics background and control-systems training are relevant but not near-term evidence of Step 7 STL expertise. To improve, add explicit PLC/Step7 projects, CREA/registration status (or plan), and any on-site/field automation experience. Also list travel/driver readiness and specific Profibus/Profinet exposure if available. **Strengths:** Mechatronics degree and control-systems foundation, Experience in industrial automation and ERP data sanitation, Systems thinking and field-level controls implementation **Critical Gaps:** No evidence of Simatic Step 7 — core JD requirement **Missing Required:** CREA (professional registration), CNH category B (driver's license), Industrial PLC programming experience

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Score reduced by missing specific platform/solution requirements (ARCHER) and lack of explicit deep cloud (Azure/AWS) operational experience despite solid systems-architecture background and leadership. Strengths in systems design, Linux and operationalization help but do not replace ARCHER and cloud admin experience. To improve, highlight concrete cloud projects (Azure/AWS) and any systems engineering/IT ops ownership, and show ARCHER experience or equivalent governance tooling exposure. **Strengths:** Systems architecture and operations experience, Leadership (Head of Engineering) and mentoring, Linux, scripting, and production troubleshooting **Missing Required:** Proven experience as System Engineer using ARCHER, Deep cloud operational experience (Azure/AWS)

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Missing RSA Archer expertise is the main deduction despite strong infrastructure and cloud familiarity; candidate has relevant system-administration and architecture skills but not the platform-specific experience required. To improve, document any Archer-like governance tooling, DB/SQL maintenance for similar platforms, or provide a brief conversion note mapping relevant experience to Archer responsibilities. **Strengths:** Systems architecture and infrastructure maintenance, Experience with cloud fundamentals and on-prem/cloud hybrid, Strong documentation and technical communication skills **Missing Required:** RSA Archer practical experience

[ANALYSIS_REPORT] **LOW** [Opencode: opencode:kimi-k2.5] Critical domain mismatch. The role demands Microsoft-centric infrastructure (VMware, Active Directory, Azure AD, Windows Server) while the candidate's expertise is Linux-first with Go, PostgreSQL, and open-source tooling. Despite 12+ years of systems thinking and infrastructure optimization, the specific Microsoft stack requirements create a substantial gap. The candidate should highlight any Windows Server or Azure exposure, but this is fundamentally a different ecosystem than his production experience. **Strengths:** Infrastructure optimization, System reliability focus, Incident resolution **Critical Gaps:** Microsoft infrastructure ecosystem completely different from Linux/Go stack **Missing Required:** 5+ years Systems Engineering title