AI Python & Java Leadership
Anson Lam ยท Portfolio
Senior GenAI / LLM Engineer | Senior Python Engineer

Building agentic RAG applications, self-hosted LLM inference systems and reliable AI workflows using LangGraph, AWS Bedrock, vLLM and NVIDIA TensorRT-LLM.

RAG on AWS EKS

Show details...

Agentic RAG running Mistral Small 24B with vLLM on AWS EKS, featuring LangGraph workflows, pgvector retrieval and persistent agent memory.

RAG on K3s Jetson

Show details...

Fully local agentic RAG using Qwen3-8B-AWQ and vLLM on NVIDIA Jetson, orchestrated with lightweight K3s Kubernetes.

Observability with Langfuse

Show details...

End-to-end tracing of agentic RAG workflows, providing visibility into LLM calls, tool execution and agent behaviour through Langfuse.

Evaluation with DeepEval

Show details...

Automated LLM evaluation using DeepEval to assess answer relevance, tool correctness and task completion in agentic workflows.

TensorRT-LLM on Jetson

Show details...

GPU-optimised local RAG inference using NVIDIA TensorRT-LLM and Llama 3.1 on Jetson, integrated with LangGraph.

Agentic Medical Research Assistant

Show details...

Agentic research assistant for exploring medical literature using LangGraph, OpenAI models, pgvector retrieval and persistent conversational memory.