Hover a card — the background comes alive. Click DiffContext to play the real thing.
A repository-scale context-selection engine for code LLMs. A sys.settrace() tracer builds gold-standard execution graphs, then prunes prompts from 35,270 → 10,747 tokens while preserving task-relevant context.
Real-time market data, localized GST tax calc, OCR bill-scanning & a normalized Postgres schema behind OAuth.
Full-stack streaming platform with TMDB integration, auth, and a content-delivery / ad-management backend.
I care about resource-efficient AI — production systems that do more with less: AST-based context selection, token pruning, and agentic pipelines that hold up under real budget and latency constraints.
I ship full-stack web apps with React, Django REST and FastAPI, and build Generative / Agentic AI systems with LangChain, LangGraph and RAG. Recent work includes SAP AI Core feedback workflows benchmarking Gemini, Mistral & GPT in production, plus LangChain RAG-retrieval contributions and Gradio demos for text-to-image models.