BJ.

Work

Projects

A collection of machine learning and generative AI systems I've designed and shipped, from retrieval pipelines to fine-tuned models and autonomous agents.

RAG + SQL Query Engine

An AI-powered question-answering system built with LlamaIndex that retrieves answers from both unstructured documents and structured SQL databases in a single query.

RAGLlamaIndexSQLLLM

Multi-Agent Content Creation with CrewAI

A collaborative content pipeline built in Python and CrewAI, using role-specific agents for outlining, writing, and validation.

CrewAIAgentsPython

Localized RAG System with ChromaDB

A topic-aware retrieval-augmented generation solution using agents and ChromaDB to deliver concise, user-specific answers.

RAGChromaDBAgents

Generative AI System Design Course

Authored a course at Educative teaching how to design production-grade generative AI systems, from architecture patterns to deployment tradeoffs.

GenAISystem DesignEducation

Fine-Tuning CNNs for Image Retrieval

Fine-tuned a convolutional neural network using Caffe to enable fast, similarity-based image retrieval from a large image database.

Computer VisionCNNTransfer Learning

Soft-Margin Kernel SVM from Scratch

Implemented a soft-margin kernelized support vector machine from scratch in Python using CVXOPT for convex optimization.

SVMPythonCVXOPT