Anti-ATS Evaluatorv1.3

[ANALYSIS_REPORT] **TOP** [3-pro] Duplicate Job ID. Same evaluation: Excellent match for skills and trajectory. **Strengths:** Self-hosted LLMs, Applied RAG/Search, Fast Learner **Inferred Skills:** RAG Architecture, Vector Databases, API Integration **Missing Nice-to-Have:** Azure AI Engineer

[ANALYSIS_REPORT] **HIGH** [2.5-Pro] Strong match on core competencies. The candidate has proven experience in Python and building AI solutions, including prompt engineering and AWS fundamentals. While he lacks direct experience with RAG, MLOps, and specific AWS services like Bedrock, his fast-learner track record suggests he could acquire these skills quickly. **Strengths:** Strong Python and software engineering skills, Hands-on experience with Generative AI and LLM integration, Full project lifecycle experience from idea to deployment **Inferred Skills:** Prompt Engineering, AI Agent Design, LangChain, OpenAI **Missing Required:** Hands-on experience with AWS solutions, especially AWS Bedrock and SageMaker, Understanding of vector databases and RAG architectures **Missing Nice-to-Have:** Experience with LLM libraries, Docker

[ANALYSIS_REPORT] **TOP** [3-pro] Duplicate Job ID. Same evaluation: Excellent match for skills and trajectory. **Strengths:** Self-hosted LLMs, Applied RAG/Search, Fast Learner **Inferred Skills:** RAG Architecture, Vector Databases, API Integration **Missing Nice-to-Have:** Azure AI Engineer

[ANALYSIS_REPORT] **TOP** [3-pro] Duplicate Job ID. Same evaluation: Excellent match for skills and trajectory. **Strengths:** Self-hosted LLMs, Applied RAG/Search, Fast Learner **Inferred Skills:** RAG Architecture, Vector Databases, API Integration **Missing Nice-to-Have:** Azure AI Engineer

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Strong match: recent hands-on LLM integrations, production automation, Python and API experience, and English fluency align well with the role. Minor gaps in explicit HuggingFace, deep RAG toolchain experience and full cloud deployment experience reduce perfection but are largely inferable from self-hosted LLM/infra work. **Strengths:** Practical LLM integrations in production, Strong Python + API experience, Systems architecture & automation at scale **Inferred Skills:** Prompt engineering, RAG architectures, Model deployment (Linux, GPU, containers), APIs and integrations, Data engineering (pandas-like) **Missing Required:** Deep proven cloud deployment experience (beyond AWS fundamentals) **Missing Nice-to-Have:** Langchain, TensorFlow/PyTorch (explicit)

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Good fit for data+AI: candidate has Python, SQL, ETL/pipeline experience and practical LLM integrations; strong product/ops orientation. Missing explicit production frameworks (FastAPI) and containerization (Docker) are material required gaps but can be learned quickly. **Strengths:** Python + SQL practical usage, Building production data flows and automation, LLM integrations and product focus **Inferred Skills:** Data pipelines/ETL design, Prompt engineering, RAG/LLM orchestration, pandas-like data manipulation **Missing Required:** FastAPI, Docker **Missing Nice-to-Have:** Airflow/Prefect/Dagster, Advanced MLOps tooling

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Partial fit: clear recent LLM/RAG experience and Python skills but missing several mandatory stack pieces (LangChain, LlamaIndex, vector DBs, PyTorch/TensorFlow, FastAPI). Multiple mandatory technology gaps lower the match for a role that requires those toolchains. **Strengths:** Hands-on LLM integrations, Python + system integration experience, Production mindset and governance rituals **Inferred Skills:** RAG design (inferred from LLM integrations), Prompt engineering, API integration, Production engineering fundamentals **Missing Required:** LangChain / LlamaIndex, Vector DBs, Deep learning frameworks (PyTorch/TensorFlow), FastAPI **Missing Nice-to-Have:** MLOps/LLMOps explicit tooling, LGPD/AI compliance experience

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Same profile as the other EY listing: strong LLM and Python foundations but missing explicit required tooling (LangChain/LlamaIndex, vector DBs, DL frameworks, FastAPI). Those mandatory gaps meaningfully reduce fit for the specified stack. **Strengths:** Practical LLM integrations, Python + data engineering, Operationalizing production systems **Inferred Skills:** RAG concepts, Prompt engineering, API integration, Production deployment fundamentals **Missing Required:** LangChain / LlamaIndex, Vector DBs, Deep learning frameworks (PyTorch/TensorFlow), FastAPI **Missing Nice-to-Have:** MLOps/LLMOps, LGPD applied to AI

[ANALYSIS_REPORT] **MEDIUM** [Copilot: GPT5-mini] Solid alignment on Python, LLM usage and production deployment concepts; candidate shows operational MLOps-like experience (self-hosted LLM infra). However limited explicit deep-learning (training/architectures) and heavy DL framework experience lower the match for a full ML/DL specialist role. **Strengths:** LLM infra and integrations, Python + engineering rigor, Productionization and observability mindset **Inferred Skills:** MLOps/infra (GPU clusters, Linux), Model deployment and monitoring, Prompt engineering and agent design **Missing Required:** Proven deep-learning model development and training experience **Missing Nice-to-Have:** Prompt fine-tuning, RAG (explicit) — partially present but not fully documented, Open-source contributions/publications

[ANALYSIS_REPORT] **MEDIUM** [2.5-Pro] This role requires a level of ML engineering specialization (fine-tuning, RAG, MLOps) that the candidate has not yet demonstrated. While he has experience integrating LLMs and building backend services, he appears to be more of a generalist systems builder than a specialized MLOps/ML engineer. **Strengths:** Experience delivering end-to-end solutions, Strong experience in AWS fundamentals, Experience building production-grade APIs **Inferred Skills:** Basic LLM prompting, API development for ML services **Missing Required:** Experience with fine-tuning, LoRA, quantization, Experience with LLMs in production, including RAG, Solid experience in MLOps

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Strong fit on infra and agent-oriented responsibilities: concrete LLM integrations, prompt engineering and experience building production systems. Missing some specific libraries (LangChain/LangGraph) and vector DB explicit experience reduce senior-level completeness but core capabilities are present and recent. **Strengths:** LLM infra + integrations, Prompt engineering and RAG concepts, Production automation and observability **Inferred Skills:** Agent architectures and orchestration, Prompt engineering, RAG and retrieval strategies, Model deployment (containers/GPU/Linux) **Missing Required:** Vector DBs (explicit) **Missing Nice-to-Have:** LangChain/LangGraph (explicit), Formal CI/CD evidence for ML pipelines

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Very good match: required Python, SQL, production LLM experience, and AWS familiarity align with the Beegol Pleno role; candidate demonstrates productionizing LLM-backed tools and data pipelines. Minor missing specifics (API Gateway/Lambda, Terraform, formal MLOps stack) are learnable and mitigated by demonstrated infra experience. **Strengths:** Production LLM projects, Python + SQL for data pipelines, Operationalizing systems at scale **Inferred Skills:** RAG and prompt engineering, Model ops and deployment (containers/GPU), ETL/pipeline design and SQL optimization **Missing Required:** Explicit experience with specific AWS services listed **Missing Nice-to-Have:** Terraform, Experiment tracking/versioning (MLflow, DVC)

[ANALYSIS_REPORT] **MEDIUM** [2.5-Pro] A solid medium-fit. The candidate aligns well with the AI Software Engineer profile, possessing strong Python skills and proven experience in building and deploying Generative AI systems. However, he lacks demonstrated experience with key modern tools like RAG/vector databases and formal MLOps pipelines, which are central to this role. **Strengths:** Expert-level skills in Python and software engineering, Direct experience with Generative AI development, Proven ability to translate business requirements into technical designs **Inferred Skills:** LangChain, Generative AI Development Lifecycle, Cloud Deployment **Missing Required:** Hands-on experience with... vector databases, Implement MLOps/LLMOps pipelines **Missing Nice-to-Have:** Experience with compliance frameworks

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Duplicate Beegol posting—same assessment: strong production LLM and data skills, good fit for Pleno role with minor gaps around specific AWS services and IaC. Candidate’s recent head-of-engineering role and hands-on LLM work make them competitive. **Strengths:** LLM in-production experience, Python + SQL + ETL skills, Operational and governance experience **Inferred Skills:** RAG architectures, Prompt engineering, Production deployment and monitoring **Missing Required:** Explicit experience with specific AWS services listed **Missing Nice-to-Have:** Terraform, ML experiment tracking

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5-mini] Strong senior-level alignment: demonstrated ability to design and run production LLM systems, agentish architectures and cost/observability considerations. Some senior-specific items (formal fine-tuning pipelines, mature CI/CD for ML and explicit agent SDK expertise) are not fully documented but many relevant skills are inferred from infra work. **Strengths:** LLM systems architecture, Production deployment and operations, Security/guardrail awareness and observability **Inferred Skills:** RAG and chunking strategies, Agent design (multiagent concepts), Token/cost optimization and model selection **Missing Required:** Explicit agent-sdk (CrewAI/Agents SDK) experience **Missing Nice-to-Have:** Fine-tuning pipelines / dataset curation evidence, Complete CI/CD examples for ML

[ANALYSIS_REPORT] **MEDIUM** [2.5-Pro] The candidate matches the staff-level seniority and has core GenAI integration experience. However, this role is focused on the cutting-edge of Agentic AI, multi-agent systems, and specific evaluation frameworks, which are beyond the scope of the candidate's demonstrated projects. He is a strong builder but may lack the specialized expertise for this forward-looking role. **Strengths:** Proven experience deploying AI architectures, Strong background in building backend software platforms (Python, Node.js), Ability to communicate complex AI concepts **Inferred Skills:** LLM Integration, Software platform development, Prompt engineering **Missing Required:** Design, develop, and deploy AI workflows and Agentic AI solutions, Expertise in data embeddings, vector databases **Missing Nice-to-Have:** Experience with Agentic AI orchestration frameworks (LangGraph, CrewAI), Kubernetes

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Same Beegol listing as other Pleno roles: candidate’s recent LLM production work, Python+SQL and pipeline experience map very well to the requirements. Only minor explicit tech gaps (specific AWS services, IaC, MLOps tools) remain. **Strengths:** Practical LLM production experience, Python + SQL proficiency, Operationalized systems and governance **Inferred Skills:** RAG, prompt engineering, ETL/pipeline design, Agent integration concepts, Model deployment on Linux/GPU **Missing Required:** Explicit experience with the specific AWS services listed **Missing Nice-to-Have:** Terraform, ML experiment tracking/versioning

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Duplicate Beegol Pleno — consistent strong fit due to hands-on LLM projects, production pipelines, and data skills; only specific infra/tooling items are not explicitly listed in the resume. Candidate’s trajectory toward AI infra and recent head role strengthen candidacy. **Strengths:** LLM infra and integrations, Python + data pipelines, Productionization and monitoring mindset **Inferred Skills:** RAG architectures, Prompt engineering, Production deployment and monitoring **Missing Required:** Explicit experience with the specific AWS services listed **Missing Nice-to-Have:** Infrastructure-as-code (Terraform), Experiment tracking / MLOps pipelines

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Another Beegol duplicate — same evaluation: strong practical alignment on LLMs, data pipelines and production experience with small infra gaps. Candidate’s recent leadership and self-teaching on LLM infra make them a strong Pleno fit. **Strengths:** Hands-on LLM projects, Python + SQL + ETL skills, Operational production experience **Inferred Skills:** RAG/prompt engineering, Agent integration concepts, Model deployment on Linux/GPUs **Missing Required:** Explicit experience with specific AWS services listed **Missing Nice-to-Have:** Terraform, MLflow/DVC or similar tracking

[ANALYSIS_REPORT] **LOW** [Copilot: GPT5-mini] Weak fit for a vision-focused engineer: candidate’s strengths are LLMs, infra and supply-chain automation, not computer-vision/deep-learning model development. The role explicitly asks for a Master’s and deep CV experience (training complex image models on GPU clusters), which are not present. **Strengths:** Strong systems and infra engineering, Python and model deployment experience, Experience operating GPU-backed model infra **Critical Gaps:** Computer Vision / Deep Learning for images - BLOCKING **Inferred Skills:** GPU cluster ops (inferred from self-hosted LLM clusters), Deep learning infra basics, Data preprocessing and embeddings knowledge **Missing Required:** Mestrado (Master's) in relevant area, Extensive CV model development experience **Missing Nice-to-Have:** Publications or open-source CV contributions, Cloud GPU cluster training evidence

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Beegol Pleno duplicate — candidate fits well due to solid production LLM experience, Python/SQL skills and pipeline knowledge; only some infra/tooling specifics are not explicit. Recent work running LLM-backed tooling and automation makes the candidate competitive for the role. **Strengths:** LLM integration in production, Python + data engineering, Operational reliability and governance **Inferred Skills:** RAG and prompt engineering, Agent architectures, Production deployment and monitoring **Missing Required:** Explicit experience with specific AWS services listed **Missing Nice-to-Have:** Terraform, Experiment tracking/versioning for ML

[ANALYSIS_REPORT] **TOP** [Copilot: GPT5-mini] Another Beegol Pleno duplicate—same strong alignment: candidate shows hands-on LLM production work, data pipelines and operational experience required for the role. Small gaps around explicit AWS services, IaC and formal MLOps tooling remain but are mitigated by infra experience and rapid learning evidence. **Strengths:** Practical LLM infra and integrations, Python + SQL + ETL capabilities, Proven production automation and governance **Inferred Skills:** RAG, prompt engineering, agent integration, Model deployment on Linux/GPU, API-based integrations **Missing Required:** Explicit experience with the specific AWS services listed **Missing Nice-to-Have:** Terraform, ML experiment tracking/versioning

[ANALYSIS_REPORT] **HIGH** [Copilot: GPT5.2] O candidato tem boa aderência em Python/SQL e já colocou um sistema real em operação (automação + dados) e também integrou LLM em uma ferramenta própria, o que cobre parte relevante do requisito de LLMs em produção. Porém, a vaga pede experiência comprovada em AWS (API Gateway/Lambda/ECS/Fargate) e práticas de produção/MLOps mais explícitas (monitoramento/logs/versionamento), que não aparecem de forma clara no currículo. **Strengths:** Automação e sistemas reais em produção (e-commerce/inventário), Integração com LLMs e construção de ferramenta própria (Node.js + LLM + SQLite), Base forte em dados (SQL + saneamento/validação de cadastros em ERP) **Inferred Skills:** ETL/data pipelines, APIs e integrações, Automação de processos, Operação de sistemas em produção, Arquitetura de sistemas, Data quality/validação, Prompting/LLM API integration **Missing Required:** Experiência comprovada em AWS (API Gateway/Lambda/ECS/Fargate ou equivalente), Vivência explícita com monitoramento/logs e práticas de produção para pipelines/modelos **Missing Nice-to-Have:** Terraform/IaC, MLOps (tracking/versionamento/CI-CD de ML)

[ANALYSIS_REPORT] **LOW** [2.5-Pro] This is a complete mismatch of profile. The role is for a Principal AI Researcher with a PhD, a strong publication record, and deep experience in fundamental GenAI research topics. The candidate is a highly skilled hands-on Systems Engineer who applies existing AI tools, but he does not have the academic background or research-focused experience required. **Critical Gaps:** Research Experience, Required Education (PhD/MSc), Publication Record **Missing Required:** PhD/MSc degree, 8+ years of experience as an AI researcher, 3+ years should be on actively developing GenAI technologies **Missing Nice-to-Have:** Proven track record of publications

[ANALYSIS_REPORT] **LOW** [Copilot: claude-opus-4.5] Significant mismatch between candidate profile (practitioner/systems engineer) and role requirements (PhD-level AI researcher). Candidate has practical LLM integration experience but lacks formal ML/AI research background, publications, and the deep theoretical foundations (NLP, CV, probability theory) required for this senior research position. **Strengths:** Strong Python/Node.js development, Practical LLM integration experience, Cross-functional technical translation skills **Critical Gaps:** No formal AI/ML research experience - role requires proven researcher track record, No PhD/MSc in relevant field - essential qualification for senior researcher role, No experience designing/training novel ML model architectures **Inferred Skills:** Python programming, Git/version control, API development, Data pipelines, Cloud basics (AWS), LLM API integration **Missing Required:** PhD/MSc degree in Computer Science or Machine Learning, Track record as ML/AI researcher, NLP expertise, Computer vision expertise, Model evaluation and interpretation, Parallel/distributed computing background **Missing Nice-to-Have:** 4+ years hands-on ML/AI research, LLM training/finetuning infrastructure experience, Publications in top-tier conferences