AI Developer – LangGraph Agents & LLM Fine-Tuning

I'm looking for an experienced AI developer to help build production-grade agentic AI systems using LangGraph and to fine-tune LLMs for domain-specific tasks. This is hands-on development work with potential for a long-term engagement. What you'll do: - Design and build multi-agent workflows in LangGraph (state graphs, tool calling, memory, human-in-the-loop, conditional routing) - Integrate agents with APIs, databases and vector stores (RAG pipelines) - Fine-tune open-source LLMs (Llama, Mistral, Qwen, etc.) using LoRA/QLoRA, PEFT or full fine-tuning - Prepare and clean training datasets, run evaluations and benchmark against base models - Deploy and serve models (vLLM, TGI, Hugging Face, or cloud GPUs such as AWS/GCP/RunPod) - Set up observability and evaluation (LangSmith, Langfuse or similar) - Write clean, documented Python code and give clear progress updates Requirements: - Proven experience with LangGraph and LangChain in real projects (please share links or examples) - Hands-on LLM fine-tuning experience (Hugging Face Transformers, PEFT, TRL, Unsloth) - Strong Python skills; FastAPI is a plus - Experience with OpenAI, Anthropic or open-source model APIs - Solid understanding of prompt engineering, RAG and evaluation methods - Good communication and ability to work independently Nice to have: - Experience with DPO / RLHF - Docker and CI/CD for ML deployment - Experience with voice AI or SaaS products To apply, please include: 1. A short summary of a LangGraph project you've built 2. A fine-tuning project you've done (model, method, results) 3. Your availability and hourly rate Proposals starting with "Dear Sir/Madam" or generic templates will be skipped.