Lead GenAI with LLM-Model tuning

Senior Python Backend Developer with deep expertise in Large Language Models (LLMs), retrieval-augmented generation (RAG), and model fine-tuning. In this role, you will bridge the gap between robust backend engineering and cutting-edge AI. You will architect scalable Python pipelines, optimize LLM performance for domain-specific tasks, and deploy production-ready AI applications. Key Responsibilities Backend Engineering: Design, build, and maintain scalable, high-performance APIs (FastAPI/Flask) and asynchronous microservices in Python.LLM Customization & Fine-Tuning: Fine-tune open-source models (e.g., Llama, Mistral) using PEFT techniques (LoRA, QLoRA) for specialized domains.Data & Pipeline Engineering: Build robust data preprocessing pipelines for tokenization, data cleaning, and dynamic embedding generation.RAG & Vector Databases: Implement advanced RAG pipelines utilizing vector databases (e.g., Pinecone, Milvus, Chroma) and optimize complex chunking and retrieval strategies.Evaluation & MLOps: Establish rigorous evaluation frameworks for LLM outputs using metrics like ROUGE, BLEU, and LLM-as-a-judge, and manage deployment lifecycles. Required Technical Skills Core Python: Production-level Python experience (asyncio, design patterns, testing frameworks).AI/Data Science: Deep familiarity with PyTorch, Hugging Face ecosystem (transformers, peft, accelerate), and Data Science libraries (NumPy, Pandas, Scikit-learn).Orchestration Frameworks: Hands-on experience with LangChain, LlamaIndex, or CrewAI.