Skip to content
View brianmcd08's full-sized avatar

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report brianmcd08

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
brianmcd08/README.md

Brian McDowell

Engineering manager with 10 years leading full-stack teams. I build with Claude Code every day, with production experience in RAG pipelines, agentic systems and LLM integration.

Currently: building Java services with Claude Code, and contributing to open source projects.

Recent work:

  • Bank message pipeline, Java and Spring Boot. Three separately deployable services (bank, processor, reconciliation), HTTP sends with retry and backoff, idempotent processing on bank-issued message ids, and RabbitMQ between processor and reconciliation. Built with Claude Code.
  • Agentic RAG chatbot with hybrid retrieval, multi-tool ReAct agent, Postgres-backed persistent memory, and LLM-as-judge evaluation. Deployed to AWS as a container-image Lambda behind API Gateway with Bedrock inference and Terraform IaC.
  • Ticket-matching Discord bot, live in a 250+ member server I run. Python and SQLite.
  • Led two Java teams at Oracle-NetSuite; designed LLM-powered duplicate detection and built the working prototype in 3 days with a volunteer team of five.

Stack: Java, Spring Boot, Spring Data JPA, Hibernate, RabbitMQ, Python, LangChain, LangGraph, FastAPI, Postgres, Docker, Terraform, AWS (Lambda, API Gateway, Bedrock), Claude API, Claude Code

📍 Durham, NC

Pinned Loading

  1. civ-rag-pipeline civ-rag-pipeline Public

    Agentic RAG chatbot with hybrid retrieval, multi-tool ReAct agent, cross-session memory, and LLM-as-judge evaluation. Deployed on AWS Lambda and Streamlit Cloud.

    Python

  2. bank-simulator bank-simulator Public

    Bank message pipeline in Java and Spring Boot: three services, HTTP retry with backoff, idempotent processing, RabbitMQ between processor and reconciliation

    Java