Anti-ATS Evaluatorv1.3

[ANALYSIS_REPORT] **MEDIUM** [Opencode: opencode:kimi-k2.5] The candidate demonstrates strong Python skills and data pipeline architecture through his market intelligence platform and inventory automation systems. He has built scalable data infrastructure processing 40-50 orders daily with minimal manual intervention. However, he lacks specific experience with Snowflake/BigQuery/Redshift, dbt, and Airflow/Dagster/Prefect. While his PostgreSQL expertise and custom Go orchestrator show data engineering capability, enterprise ATS will flag the missing toolchain. **Strengths:** Python, Data pipeline architecture, Custom orchestrator, Data quality controls **Missing Required:** 6+ years professional data engineering title

[ANALYSIS_REPORT] **LOW** [Opencode: opencode:kimi-k2.5] Candidate has strong data pipeline and Python skills, but this role requires deep Azure ecosystem expertise including Qlik Replicate, QEM, SQL Server, and Oracle. His experience is built on Linux, Go, PostgreSQL, and open-source tooling - fundamentally different stack. The Microsoft/Azure ecosystem gap is too severe for meaningful ATS matching. **Strengths:** Python, Data integration, PostgreSQL **Critical Gaps:** Azure cloud ecosystem, Microsoft data stack

[ANALYSIS_REPORT] **MEDIUM** [Opencode: opencode:kimi-k2.5] Strong alignment on Python, AI pipelines, and LLM integration. Candidate has practical RAG experience, prompt engineering, and built production AI systems. However, he lacks traditional ML frameworks (TensorFlow, PyTorch, Scikit-learn) and specific orchestrators like Airflow. His ML experience is LLM-focused rather than classical ML. **Strengths:** Python, LLM pipelines, RAG, Prompt engineering, AI integration

[ANALYSIS_REPORT] **LOW** [Opencode: opencode:kimi-k2.5] Candidate has relevant AI/LLM skills but this is a pure Microsoft/Azure stack role requiring Copilot Studio, Azure Data Factory, Databricks, Microsoft Fabric, and Azure AI Foundry. His entire infrastructure is Linux/Go/PostgreSQL/open-source. The ecosystem mismatch is absolute. **Strengths:** RAG, Embeddings, Python, LLM APIs **Critical Gaps:** Azure ecosystem, Microsoft Copilot Studio, Power Platform

[ANALYSIS_REPORT] **LOW** [gemini-3.1-pro-preview] This is a pure enterprise IT operations and sysadmin role focused heavily on patch management and legacy/enterprise infrastructure. The candidate is a systems builder and AI architect, not an IT support/patching analyst. He lacks the enterprise patching tools (Satellite, Spacewalk, AWX) required for this specific daily workflow. **Strengths:** Linux, Bash, Docker **Critical Gaps:** Deep enterprise patch management experience, Overnight shift IT ops experience **Missing Required:** Ansible, Enterprise patching tools

[ANALYSIS_REPORT] **LOW** [gemini-3.1-pro-preview] This role requires managing enterprise physical infrastructure, VMware, and traditional corporate storage (LUN, Fibre Channel). The candidate operates in lightweight, modern environments (1vCPU cloud instances, Go, Node.js) and lacks the required proprietary hardware storage and Windows Server administration experience. **Strengths:** Linux, Bash, SQL **Critical Gaps:** Enterprise hardware storage management, Windows infrastructure administration **Missing Required:** VMware, Windows Server, Corporate Storage provisioning

[ANALYSIS_REPORT] **HIGH** [Opencode: opus-4-5] Strong alignment: candidate has Python, Go, Bash scripting; SaaS integration experience (built automations connecting various systems); OAuth 2.0/OIDC/SSO knowledge explicitly demonstrated; API/webhook experience; Linux administration; automation pipelines. LLM integration for operational workflows matches AI assistant requirement. 8 years total experience partially met through combined technical roles. Missing: specific SaaS platforms (Salesforce admin, HubSpot admin, Zendesk), GCP experience (has AWS), Kubernetes depth, formal IT Engineering title. **Strengths:** Python, Go, Bash scripting, OAuth 2.0/OIDC/SSO implementation, API and webhook automation, LLM-driven workflows, Linux proficiency, Event-driven automation **Missing Required:** 8 years IT Engineering/Systems Engineering title experience, GCP experience

[ANALYSIS_REPORT] **LOW** [gemini-3.1-pro-preview] This is a highly specialized DevOps/SRE role centered around Kubernetes (EKS) and GitOps (ArgoCD) at enterprise scale. While the candidate understands CI/CD, Docker, and Linux, he explicitly lacks the deep Kubernetes, Helm, and AWS ecosystem expertise required to manage these specific clusters. **Strengths:** Linux, Docker, CI/CD fundamentals **Critical Gaps:** Enterprise Kubernetes cluster management, GitOps implementation **Missing Required:** Kubernetes (EKS), Helm, AWS architecture

[ANALYSIS_REPORT] **LOW** [gemini-3.1-pro-preview] This is a classical industrial automation engineering role requiring expertise in Siemens PLCs (PCS 7) for the automotive industry. Despite the candidate having a Mechatronics degree, his current trajectory is entirely in software automation, AI, and web systems, not industrial factory PLCs. **Strengths:** Mechatronics Engineering Degree, Process Control logic **Critical Gaps:** Siemens industrial software stack, Factory floor commissioning experience **Missing Required:** PCS 7

[ANALYSIS_REPORT] **LOW** [gemini-3.1-pro-preview] This is a legacy banking application support role requiring C#/.NET or Cobol, and Kafka. The candidate works with modern open-source stacks (Go, Node.js, Python) and lacks the required proprietary banking technologies. **Strengths:** SQL, API Integration, System analysis **Critical Gaps:** Legacy banking stack (.NET/Cobol) **Missing Required:** Cobol or .NET/C#

[ANALYSIS_REPORT] **LOW** [Opencode: opus-4-5] Complete domain mismatch: Mid-Career Avionics Systems Engineer requires electrical/avionics engineering for commercial aircraft. While candidate has Mechatronics Engineering degree (adjacent), the specific requirements around ARP-4754, ARP 4761, RTCA DO-160, flight systems (Air Data, Inertial, Flight Management, Thrust Management), and CREA registration are completely different domain. This is aerospace/aviation hardware engineering, not software/systems architecture. **Strengths:** Mechatronics Engineering degree (hardware/control systems background) **Critical Gaps:** Avionics/aerospace domain expertise, CREA registration requirement, Aircraft systems experience **Missing Required:** Electrical/Computer Engineering degree preferred, Avionics systems experience, Product development life cycle V-model ARP-4754

[ANALYSIS_REPORT] **TOP** [Opencode: opus-4-5] Strong alignment: candidate has AI systems experience with LLM APIs (Claude, Gemini, OpenAI SDK), demonstrated agent-like system building (job intelligence platform with orchestrator), production deployment experience, async work tools familiarity (Git, remote work). Node.js experience present. Django is mentioned but as 'or' with Node which candidate has. Remote async culture with Slack/Linear/GitHub matches candidate's demonstrated work style. 'Upper medium to senior' level is flexible. **Strengths:** LLM and agent systems experience, Node.js proficiency, Production AI systems deployment, Remote work tools familiarity, Excellent English

[ANALYSIS_REPORT] **HIGH** [gemini-3.1-pro-preview] The candidate is a strong fit for the core requirements (Python, LangChain, GenAI APIs, Vector DBs, Microservices). However, the ATS score is capped at 70 because his resume lacks the specific Python API frameworks (FastAPI/Flask) requested, despite him building equivalent servers in Go/Node. **Strengths:** LangChain, OpenAI/Claude APIs, Python, Microservices, RAG **Missing Required:** FastAPI or Flask

[ANALYSIS_REPORT] **TOP** [gemini-3.1-pro-preview] Excellent functional match for the candidate. He essentially built a custom multi-agent orchestrator from scratch. However, his 'first principles' approach means his resume lacks enterprise framework keywords like LangGraph and AWS EC2/S3, capping his ATS score at 70. **Strengths:** LLM API Integration, Custom Orchestrators, RAG, Node.js/Python, Prompt Engineering **Missing Required:** LangGraph

[ANALYSIS_REPORT] **HIGH** [gemini-3.1-pro-preview] Strong alignment with RAG, LangChain, Python, and SQL requirements. The candidate's experience with SQLite/PostgreSQL vectors maps well here. Score is capped due to missing specific API framework keywords (FastAPI/Flask) and specific cloud platforms (Azure/GCP). **Strengths:** RAG Pipelines, Python/SQL, LangChain, Prompt Engineering **Missing Required:** FastAPI or Flask

[ANALYSIS_REPORT] **MEDIUM** [gemini-3.1-pro-preview] The candidate has the exact degree profile (Engineering) and AI/LLM experience required. However, the strict 'fine-tuning' requirement caps the score, as his resume focuses on prompt-tuning/PID logic rather than explicit weights fine-tuning of models. **Strengths:** LLM Integration, Python, Engineering Degree, Relational Databases **Missing Required:** Fine-tuning models

[ANALYSIS_REPORT] **HIGH** [gemini-3.1-pro-preview] The candidate's custom scraper and orchestrator heavily utilized agentic logic (similar to Plan-and-Execute, ReAct, and Tool Use/Function Calling). However, he lacks specific conversational platforms (Blip, Dialogflow) and uses first-principle terms instead of the trendy framework keywords requested. **Strengths:** Python, OpenAI/Claude/Gemini API, Prompt Engineering, Agentic orchestration concepts **Missing Required:** Chatbot platforms (Blip/Dialogflow)

[ANALYSIS_REPORT] **TOP** [Opencode: opencode:kimi-k2.5] Excellent alignment. Python, API architecture (built production webserver), distributed systems understanding (orchestrator), RAG, LLM integration, OAuth/JWT (implemented from scratch), Docker, CI/CD. Strong match for backend AI engineering requirements. **Strengths:** Python, API architecture, Distributed systems, RAG, OAuth/OIDC, LLM integration, Docker

[ANALYSIS_REPORT] **MEDIUM** [Opencode: sonnet-4-5] Candidate demonstrates strong RAG pipeline design, LLM integration (Claude/Gemini/OpenAI APIs), and production deployment experience. However, lacks AWS-specific services (Bedrock, SageMaker), Java/Spring Boot, and formal MLOps experience. To improve: add AWS certification or projects, highlight any Java exposure, frame the orchestrator project as MLOps-adjacent (state management, monitoring, cost optimization). **Strengths:** RAG pipeline design and implementation, LLM API integration (OpenAI/Gemini/Claude), Agent orchestration (custom Go orchestrator), Cost/token optimization, Production deployment experience **Critical Gaps:** No AWS cloud architecture experience, No Java/Spring Boot backend development **Missing Required:** AWS services experience (Bedrock/SageMaker), Java/Spring Boot

[ANALYSIS_REPORT] **LOW** [Opencode: sonnet-4-5] Candidate has strong NLP/Transformer integration experience (LLM APIs), RAG architecture, embeddings/vector search (inferred from RAG work), and event-driven systems thinking. Critical gaps: 6+ years Java/Spring requirement, no Azure/multicloud, no Kafka, no formal ML engineering title. To improve: emphasize any asynchronous processing in orchestrator, frame data pipeline work as event-driven, mention Docker if used, add Java fundamentals course. **Strengths:** RAG architecture design and implementation, LLM provider integration (OpenAI/Gemini APIs), Embeddings and vector search (inferred), Cost/token optimization, CI/CD concepts (Git-based workflows) **Critical Gaps:** 6+ years Java enterprise development requirement not met, No job title containing 'Engineer' or 'ML', No multicloud (AWS + Azure) experience **Missing Required:** 6+ years Java/Spring experience, Complete undergraduate degree (Mechatronics may not pass ATS filter expecting CS), Apache Kafka, Kubernetes/ECS/EKS

[ANALYSIS_REPORT] **HIGH** [Opencode: opus-4-5] Strong alignment on multiple dimensions: LLM pipeline design matches RAG requirement, prompt engineering with statistical validation ('PID-control-inspired prompt tuning, 26% to 2.9% variance'), production deployment on constrained infra, PostgreSQL, Docker, CI/CD. LangChain listed in skills. However: role requires 'Advanced Python proficiency' with specific FastAPI/Pydantic which candidate doesn't explicitly show. 5+ years backend experience requirement - candidate's formal years are in non-SE titles. Playwright/browser automation: candidate has Puppeteer which is equivalent. **Strengths:** LLM pipeline design with evaluation metrics, RAG knowledge, Production deployment on constrained infrastructure, Puppeteer/browser automation, Prompt engineering with statistical validation **Missing Required:** 5+ years practical software development in Backend, FastAPI for high-performance async APIs

[ANALYSIS_REPORT] **LOW** [Opencode: opus-4-5] Role is traditional ML Engineering focused on 'algorithms that learn and make predictions' - training, statistical analysis, fine-tuning models. Candidate's experience is primarily AI integration/orchestration (using LLMs via API) rather than training/building ML models from scratch. 'Design machine learning systems' and 'Research and implement appropriate ML algorithms' implies deeper ML/data science fundamentals than candidate demonstrates. Statistical analysis experience from quantitative trading partially applies. **Strengths:** Statistical analysis background (trading strategies), Python proficiency, Data pipeline experience **Critical Gaps:** Traditional ML engineering experience (training, fine-tuning, algorithm development) **Missing Required:** ML algorithm implementation experience, Model training and retraining experience, Statistical analysis for ML

[ANALYSIS_REPORT] **LOW** [Opencode: opencode:kimi-k2.5] This is a hard pivot from the candidate's trajectory. While they have built an AI scoring pipeline and worked with LLMs, this role requires deep ML engineering expertise—algorithm design, statistical analysis, and extending ML libraries. The candidate's AI work is applied/infrastructure-focused (API integration, RAG pipelines) rather than core ML research and algorithm development. The resume shows 'AI Integration' and 'LLM pipelines' but not 'Machine Learning Engineer' depth. Missing hard requirements: statistical modeling expertise, ML algorithm development from scratch, and academic ML background. **Strengths:** AI pipeline architecture, LLM integration experience, RAG implementation, built production data pipeline **Critical Gaps:** No formal ML Engineer title or equivalent, No CS/ML degree, No production ML model training from scratch, Algorithm development vs API integration gap **Missing Required:** statistical analyses, fine-tuning ML models, ML libraries extension

[ANALYSIS_REPORT] **LOW** [Opencode: opencode:kimi-k2.5] The candidate brings strong architectural thinking and cloud/infrastructure knowledge, but this role is heavily Java/Spring enterprise stack—completely absent from the resume. The candidate's strengths are in Go, Node.js, and lean systems. This role demands MVC, hexagonal architecture, Spring Boot, and heavy governance/auditing experience. 'Business-technical bridge' fits, but 'Java enterprise architect' does not. The candidate could handle the cloud and infrastructure aspects but lacks the core Java ecosystem expertise. **Strengths:** Cloud infrastructure design, Linux environments, containers knowledge, security principles, networking basics, REST API design **Critical Gaps:** No Java ecosystem experience, No enterprise governance background, No regulated environment work **Missing Required:** Java 8+, Spring Boot/MVC/Data/Security, architecture governance, auditing documentation

[ANALYSIS_REPORT] **MEDIUM** [Opencode: opencode:kimi-k2.5] Strong alignment with the candidate's core superpower: business-technical bridge. The role emphasizes 'technical-strategic bridge,' 'value propositions,' and 'C-level presentations'—exactly what the candidate has done across supply chain, finance, and e-commerce. The candidate has defined scope, written business cases, and translated executive intent into technical requirements. However, gaps exist: 'low-code' platforms (SoftExpert) are not in the resume, and 'Big Four consulting' experience is missing. The candidate's 'strategic alliance' experience is limited to their own venture. **Strengths:** Business-technical translation, C-level communication, ROI/Payback/NPV business cases, value proposition design, strategic solution architecture, cross-functional leadership **Missing Required:** SoftExpert suite knowledge