I am an AI/ML Engineer specializing in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) systems, and inference performance optimization.

I help startups, developers, and businesses build production-ready AI applications, fix broken LLM code, and optimize local or cloud model deployments for speed and cost efficiency.

How I Can Help You:
• Custom RAG Development: Connect LLMs to your private business data, PDFs, or databases with high precision and low hallucination.
• Inference & Cost Optimization: Accelerate local/cloud LLM throughput, reduce API costs, and tune latency using modern frameworks (vLLM, Ollama, CUDA optimization).
• Code Debugging & Unblocking: Fix bugs and logical bottlenecks in your LangChain, LlamaIndex, or custom Python ML scripts.
• AI Agents & Integrations: Implement function calling, structured outputs, and automated workflows into your existing software.

Tech Stack & Tools:
Python, PyTorch, LangChain, LlamaIndex, Hugging Face, vLLM, CUDA, Vector Databases (Pinecone, Qdrant, Chroma, FAISS).

Whether you need a quick 1-hour code debugging session, a prototype built, or an end-to-end RAG pipeline implemented, feel free to reach out to discuss your project!