Ai Lead - Communication
CurrentDeveloped and supervised the use case of Large Language Models (LLMs). Responsibilities included overseeing LLM fine-tuning with Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), enhancing AI response quality and data accuracy through data annotation and synthetic data generation. Integrated Retrieval-Augmented Generation (RAG) for better informed responses. Developed performance monitoring dashboards and managed LLM deployment lifecycle.Tech stacks:Python, SQL, HTML, Javascript, Gitlab, Postgre, Docker.Frequently Used Libraries/Frameworks:PyTorch, FastAPI, Huggingface, Dash, vLLM, Gradio, etc.