π LLM Engineer | Generative AI Developer | NLP & RAG Expert
π¬ Specializing in Fine-tuning LLMs, RAG Pipelines, AI Agents, and Model Benchmarking
- π₯ Highlights: Trained a LLaMA-2 13B model on medical Q&A
- π» Stack: PyTorch, Hugging Face, LoRA, PEFT, DeepSpeed
- π Repo: LLaMA Fine-tuning
- π₯ Highlights: Built an enterprise RAG chatbot with FAISS & Pinecone
- π» Stack: LangChain, ChromaDB, OpenAI API, Streamlit
- π Repo: RAG Pipeline
- π₯ Highlights: Compared GPT-4, LLaMA, and Mistral on latency & cost
- π» Stack: OpenAI API, vLLM, ONNX, DeepSpeed
- π Repo: LLM Benchmarking
πΉ LLMs: GPT-4, LLaMA, Mistral, Falcon
πΉ ML Frameworks: PyTorch, TensorFlow, Transformers
πΉ Data Retrieval: FAISS, Pinecone, ChromaDB
πΉ Backend: FastAPI, Flask, Streamlit
πΉ Deployment: Docker, Kubernetes, AWS Lambda