Staff AI Systems Engineer - Post-Training RL & Optimization

Remanence; Paris; Hybride; EUR 90 000 - 130 000; Plein temps

Avantages offerts par ce poste

Visa sponsorship

Relocation support

Hybrid work setup

Equity

Résumé du poste

Remanence seeks a Member of Technical Staff for post-training and reinforcement learning to own and optimize the training and evaluation loops for advanced AI systems located in Paris or London. You will work on supervised fine-tuning, RL methods like PPO, GRPO and SDPO, and push throughput and GPU efficiency across distributed training.

The role blends research and systems engineering in a fast-paced environment with visa sponsorship and relocation support.

Qualifications

• Strong programming skills and quantitative reasoning.
• Experience with learning algorithms and system interplay.
• No requirement to know every framework listed.

Responsabilités

• Implement and improve supervised fine-tuning, preference optimization, and RL methods such as PPO, GRPO and SDPO.
• Own the training loop from rollout generation and reward computation through policy updates, weight synchronization, and checkpointing.
• Improve throughput, GPU utilization, and memory efficiency through batching, parallelism, communication overlap, and asynchronous execution.
• Profile bottlenecks and investigate numerical instability, stale-policy effects, and training-inference discrepancies. Verify that optimizations preserve learning behavior.
• Occasionally deploy models in client environments and hill-climb alongside their teams: analyze real failures, refine rewards and training data, and iterate on task success, latency, and inference cost.

Outils

PyTorch

Miles

NVIDIA Molt

Megatron-LM

vLLM

Ray

Description du poste

Remanence seeks a Member of Technical Staff for post-training and reinforcement learning to own and optimize the training and evaluation loops for advanced AI systems located in Paris or London. You will work on supervised fine-tuning, RL methods like PPO, GRPO and SDPO, and push throughput and GPU efficiency across distributed training.

The role blends research and systems engineering in a fast-paced environment with visa sponsorship and relocation support.