Projects

Three projects, end to end.

Each project ships through the full pipeline: training data, model, orchestration, evaluation, and deployment. Click any card for the architecture and the numbers.

iRacing AI Race Strategist

Shipped

Fine-tuned Llama 3.1 8B that calls race strategy in real time — and the eval harness that proved it works.

  • Llama 3.1 8B
  • QLoRA
  • transformers / peft
  • LM Studio
  • GGUF q4_k_m
  • Piper TTS

Read more

AWS Bedrock Agentic Shopping Assistant

Live

Autonomous shopping agent on AWS Bedrock — natural-language search, tool-calling, fully Terraform-provisioned.

  • AWS Bedrock Agents
  • Lambda
  • DynamoDB
  • API Gateway
  • S3
  • IAM

Read more

Titanic Historical RAG

Live

A RAG search engine over the 1912 Titanic inquiries that surfaces contradictions between witnesses instead of hiding them.

  • OpenAI text-embedding-3-large
  • Pinecone
  • Claude Haiku 4.5
  • FastAPI
  • SQLite
  • pymupdf

Read more