Project focus

Own the end-to-end cloud fine-tuning of open-source LLMs on Azure - covering both Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT), from data preparation through training, evaluation, and deployment. The role involves working with sensitive data under strict internal access controls.

Key skills and Experience required

- 5+ years of engineering experience, including 2+ years hands-on LLM fine-tuning
- Strong Python and PyTorch
- Production experience with Azure Machine Learning and Azure AI Foundry (managed compute, serverless fine-tuning, online endpoints, GPU quotas)
- Hugging Face stack (transformers, peft, trl, datasets, accelerate); LoRA/QLoRA and bitsandbytes 4-bit quantization




- SFT delivery plus working knowledge of RL/preference methods (RFT, GRPO/PPO, DPO) and reward/grader design
- Training-data engineering: JSONL/chat formats, curation, deduplication, split hygiene, leakage prevention
- Evaluation rigor: task metrics, LLM-as-judge, and reading training/validation curves
- Linux, Git, containers, and cloud GPU workflows
- Preferred: DeepSpeed/multi-node training, quantization & serving (GGUF/llama.cpp, vLLM, Ollama), Azure OpenAI fine-tuning API, RAG/GraphRAG, infrastructure-as-code (Bicep/Terraform), and Responsible-AI practices

#J-18808-Ljbffr

📌 AI Engineer - LLM Fine-Tuning on Azure (España)
🏢 Darwin Recruitment
📍 España