Research Engineer, Forge

MistralAmsterdamRemoteFull-time4 Sept 2026

Mistral is hiring a Research Engineer for its Forge team to build reliable training and deployment workflows for model adaptation and post-training. The role involves working end-to-end across CPT/SFT/RL/distillation, evaluation, data, and infrastructure, collaborating with scientists and engineers. Requires strong Python skills, experience with PyTorch/JAX, and LLM training or post-training experience.

What you'll do

Build and improve post-training and evaluation workflows (CPT/SFT/RL/distillation), turning prototypes into repeatable Forge recipes.
Develop tools and pipelines for synthetic data generation, data curation, training, evaluation, and deployment.
Debug and harden large-scale ML systems: distributed training, scheduling/execution, checkpointing, observability, and reproducibility.
Improve the Forge codebase via clear APIs, tests, documentation, and maintainable abstractions.
Push the frontier of our RL training stack (e.g., high-throughput async rollout and scalable post-training systems at frontier-model scale).
Make sure Forge deployment is seamless and adaptable to a diversity of clients (hardware access, software stack, cloud and on-premises).
Partner with researchers and infrastructure engineers to translate bottlenecks into concrete system improvements.

What you need

Must-have

PythonPyTorchJAXLLM trainingPost-trainingFine-tuningReinforcement LearningDistillation

Nice-to-have

FSDPDeepSpeedMegatronSLURMRayKubernetesKueueKarpenter

Soft skills

CommunicationHigh agencyLow egoTeam-spiritedCollaborativeCreativeProblem solving

Research EngineerAIMachine LearningLLMPost-trainingPythonPyTorchJAXRemoteFull-time

/What you'll do

/What you need

Must-have

Nice-to-have

Soft skills

What you'll do

What you need