Building intelligent systems that reason, retrieve context, and automate complex engineering workflows.
I'm an AI Engineer passionate about building autonomous systems that extend the capabilities of Large Language Models beyond conversation.
My work focuses on combining LLMs, Retrieval-Augmented Generation (RAG), vector search, and workflow orchestration to create AI systems that understand context, make decisions, and interact with real software infrastructure.
I enjoy solving engineering problems where AI can automate repetitive workflows, accelerate developer productivity, and operate reliably in production environments.
A production-oriented multi-agent system that automatically diagnoses GitHub Actions failures, retrieves similar historical incidents using vector search, generates fixes, and opens pull requests with minimal human intervention.
Highlights
- LangGraph-based autonomous workflow
- Repository Structure Index (RSI) for repository understanding
- Episodic memory using PostgreSQL + pgvector
- Few-shot RAG for failure diagnosis
- Dockerized deployment with GitHub webhook integration
Impact
- 🚀 Reduced debugging time by 65%
- 🤖 Automatically resolved 60–75% of common CI/CD failures
Built an end-to-end system that transforms raw user feedback into actionable engineering tasks using NLP clustering and semantic similarity.
Highlights
- Chrome Extension + CLI Agent + Dashboard
- Semantic clustering using cosine similarity
- Automatic code module mapping
- Intelligent feedback deduplication
Impact
- ⚡ Reduced manual code-update effort by 40%
- 🚀 Reduced feedback-to-deployment cycle from hours to under 10 minutes
Python • OpenAI API • LangChain • LangGraph • RAG • Prompt Engineering • Vector Search • pgvector • Scikit-learn • NLP
FastAPI • Node.js • Express.js • REST APIs • WebSockets • SSE
React • JavaScript • TypeScript • HTML • CSS
PostgreSQL • MongoDB • MySQL
Docker • GitHub Actions • Git • AWS • Azure • GCP
- 🥇 Winner — Code and Solve Challenge
- 🥇 Winner — Hack to Future
- 🏅 Top 6 — Agentathon (PES University)
- 💻 Solved 300+ LeetCode problems
- 📈 LeetCode Max Rating: 1564
I'm always interested in collaborating on projects involving:
- Autonomous AI Agents
- LLM Applications
- Retrieval-Augmented Generation (RAG)
- AI Infrastructure
- Developer Tools
- Open Source AI
If you're building in this space, feel free to reach out!

