LLM Engineer — Fine-Tuning & Training

Mistral AI is hiring an LLM Engineer to work on model fine-tuning, alignment, and training infrastructure. You will contribute to making Mistral's models more capable, efficient, and reliably aligned for enterprise deployment.

Responsibilities

• Design and run supervised fine-tuning and RLHF training pipelines
• Implement LoRA and QLoRA parameter-efficient fine-tuning methods
• Build evaluation benchmarks to measure fine-tuned model quality
• Optimise training efficiency on distributed GPU clusters
• Collaborate with research team on alignment techniques

Requirements

• Strong Python and PyTorch skills
• Experience with LLM fine-tuning (SFT, DPO, RLHF)
• Familiarity with parameter-efficient methods (LoRA, QLoRA, adapters)
• Experience with distributed training (DeepSpeed, FSDP)