Building production agentic AI systems with LangGraph, RAG, and MCP for semiconductor R&D. Published researcher. Background includes Intel Dublin, Nvidia, and AMD.
Production-grade AI agent that indexes semiconductor IP documentation and generates ECO recommendations -- deployed live on AWS Dublin.
5-node LangGraph StateGraph with conditional edges, 6 bound tools, deterministic regex routing (8 rules) before LLM fallback. 3 specialist sub-agents (Timing, DRC, Physical) with cross-domain context sharing.
pgvector semantic search + BM25 keyword search + Reciprocal Rank Fusion over semiconductor IP docs. Production ETL: download, parse, SHA256 dedup, metadata enrichment, batch embed.
FastMCP server (4 tools + 1 resource) exposing EDA search to Claude Desktop/Cursor via SSE. A2A Agent Card discovery + task delegation. 14 FastAPI REST endpoints.
3-layer guardrails: hallucination detection (0.3 threshold), 8-rule domain accuracy validator, format compliance. Cost router, semantic cache (0.95 cosine). LangSmith per-query tracking.
IEEE format, 12 pages, 8 figures. Benchmarks 4 retrieval methods (Vector, MultiVector, RAPTOR, ColBERT) across 3 EDA corpora. Quantifies how domain-specific chunking and metadata enrichment improve retrieval quality for semiconductor documentation.
Open to Lead AI Engineer, EDA + AI, and Physical Design roles. Previously based in Dublin (Intel Leixlip, 2014-2016) -- eligible for Ireland Critical Skills Employment Permit.