I'm a software engineer based in San Bernardino, California, passionate about understanding how things work — not just using them. I love going deep on systems, ML pipelines, and developer tooling.

• 🔭 Currently building Smart Doc Search — a RAG-based PDF Q&A app using LangChain, FAISS & HuggingFace
• 🌱 Actively contributing to open-source — starting with FastAPI documentation
• 🎯 Goal: ML Infrastructure Engineering — working toward understanding retrieval pipelines, vector search, and LLM serving
• 🧠 Currently exploring: FAISS index types, BM25, Reciprocal Rank Fusion, cross-encoder reranking
• ⚡ I learn by asking why — not just how
• 💬 Ask me about Python, RAG pipelines, or getting started with open source

ML / AI Stack: LangChain · FAISS · HuggingFace Transformers · Streamlit · Groq API · Sentence Transformers

A Streamlit RAG application for semantic search over PDF documents

• Upload PDFs → chunk → embed → index with FAISS
• Semantic retrieval using sentence-transformer embeddings
• Extractive QA via HuggingFace Transformers + Groq API backend
• Guardrails for scanned/image-only PDFs
• Built to understand retrieval pipelines end-to-end, not just use them

Python LangChain FAISS HuggingFace Streamlit Groq

Currently contributing to FastAPI — starting with documentation improvements as a learning path into production Python codebases.