
AI Engineer | Production RAG, multi-agent systems, LLM evals | LangGraph, MCP | AWS Community Builder
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
advanced-rag-engineering
May 24, 2026 – Present
Production RAG system in Python: Haystack pipelines, FastAPI SSE streaming, Qdrant hybrid retrieval, OpenAI embeddings, DeepEval golden-set evaluation, and Langfuse tracing. Includes latency benchmarks (P50/P95 TTFT), retrieval failure-mode analysis, and chunking-strategy decision logs.
View Projectproperty-maintenance-agent
May 9, 2026 – Present
Eval-first AI agent that triages property maintenance emails. The real work is the eval system around it: trace-driven error analysis, code graders and validated LLM-as-judge (TPR/TNR), component and end-to-end evals, a failure taxonomy, and a CI regression gate. LangGraph, FastAPI, Langfuse.
View Projecttutorclaw-mcp
April 15, 2026 – Present
MCP server for TutorClaw, an AI-powered tutoring system that teaches programming through PRIMM-Lite pedagogy, adaptive learning, and tiered content access
View Projectsupport-fte-evals
January 31, 2026 – Present
Eval-driven Customer Support FTE using OpenAI Agents SDK. Multi-agent routing, guardrails, and systematic quality evaluation.
View Projectsidekick-agent-langgraph
September 30, 2025 – September 30, 2025
Autonomous AI assistant built with LangGraph that executes complex multi-step tasks through web browsing, file operations, Python code execution, and research. Features worker-evaluator architecture with Playwright integration, Gradio UI, and persistent memory for intelligent task completion.
View Projectmulti-agent-hotel-assistant
September 27, 2025 – September 29, 2025
AWS-powered hotel booking multi-agent assistant built with Strands Agents, Amazon Bedrock AgentCore, A2A protocol, MCP, Bedrock Knowledge Base, serverless Lambda integrations, and AWS CDK. Provides natural-language hotel search, price discovery, booking, and policy advisory.
View Projectbedrock-hotel-agent
June 9, 2025 – June 26, 2025
AI-powered hotel booking agnet using Amazon Bedrock, Lambda, and DynamoDB. Built with AWS CDK (TypeScript) and guided by real-world customer experience workflows.
View Projectretail-ai-insights
May 22, 2025 – June 6, 2025
A cloud-native AI system for retail demand forecasting and product recommendations using AWS Bedrock, Personalize, Lambda, EC2, and AWS CDK (TypeScript)
View ProjectDocInsight
April 2, 2025 – April 25, 2025
This project is a serverless MLOps pipeline for AI-driven document processing, automating text extraction, refinement, and analysis. It leverages AWS Textract, SageMaker, and OpenSearch, along with AWS CDK for infra provisioning.
View Projectaws-bedrock-support-chatbot
March 7, 2025 – March 16, 2025
AI-powered customer support chatbot built with AWS Bedrock, API Gateway, Lambda, and DynamoDB. Features smart routing, human escalation, and real-time monitoring.
View ProjectCultural Fit Analysis
The candidate's project portfolio is heavily skewed towards AI/ML, MLOps, and backend/cloud infrastructure development, primarily using Python and TypeScript/JavaScript. While these technologies are valuable, the target role is 'Frontend Developer'. There is a significant mismatch between the candidate's demonstrated project experience and the specific requirements of a frontend role. The projects do not showcase typical frontend skills such as modern UI frameworks (React, Angular, Vue), state management, responsive design, accessibility, or deep browser-side performance optimization. This indicates a potential cultural fit challenge for a dedicated frontend team, as their expertise lies in a different domain.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a strong problem-solving orientation and a systematic approach to development, particularly in AI/ML. The emphasis on evaluation systems, failure analysis, and performance metrics suggests a detail-oriented and quality-focused individual. However, without direct assessment data, specific soft skills like teamwork, communication, or stress handling cannot be definitively evaluated.