ML Systems Engineer — RL & Post-Training Pipelines

Remanence; Paris (TX); Hybrid; USD 135,000 - 203,000; Full time

Benefits offered by this job

Visa sponsorship

Relocation support

Hybrid setup

Job summary

Remanence is pioneering enterprise AI, building intelligent systems that learn continuously from real-world execution. We seek a Member of Technical Staff - Post-training / RL to own post-training methods, training loops, and scalable RL experiments in a hybrid setup with sponsorship for candidates joining us in Paris or London.

You will work on supervised fine-tuning, PPO/GRPO/SDPO, reward computation, and performance optimization across GPUs, with an emphasis on reliability and real-world

Qualifications

• Experience with large-scale RL and post-training methods may be beneficial.
• Strong programming and quantitative reasoning.
• Ability to move from experiments to profiler traces.

Responsibilities

• 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.

Tools

PyTorch

Miles

NVIDIA Molt

verl

FSDP

Megatron-LM

vLLM

SGLang

Ray

NVIDIA Nsight Systems

CUDA

Triton

CuTE

PyTorch Profiler

Job description

Remanence is pioneering enterprise AI, building intelligent systems that learn continuously from real-world execution. We seek a Member of Technical Staff - Post-training / RL to own post-training methods, training loops, and scalable RL experiments in a hybrid setup with sponsorship for candidates joining us in Paris or London.

You will work on supervised fine-tuning, PPO/GRPO/SDPO, reward computation, and performance optimization across GPUs, with an emphasis on reliability and real-world