Post-Training RL Engineer - Hybrid, Scale AI Training

Axiōma Search; Greater London; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

Stealth AI Lab in London or Paris (Hybrid) is seeking a Member of Technical Staff – Post-training / RL to improve models after their initial training. You will advance reinforcement learning and post-training methods while strengthening the systems that run large-scale experiments.

You’ll work across both learning algorithms and the infrastructure, from RL experiments to GPU profiling, identifying bottlenecks and ensuring system changes do not alter how the model learns.

Qualifications

• Strong programming and quantitative problem-solving skills.
• Hands-on experience with PyTorch and model training.
• Understanding of reinforcement learning and/or post-training for LLMs.
• Experience with distributed training and GPU systems.
• Strong experimental judgement.
• Ability to work across ML research and systems engineering.

Responsibilities

• Build and improve supervised fine-tuning, preference optimisation and RL methods.
• Work with approaches including PPO, GRPO and SDPO.
• Own training loops from rollout generation through to policy updates and checkpointing.
• Improve training throughput, GPU utilisation and memory efficiency; profile and fix bottlenecks across distributed training.
• Investigate instability and differences between training and inference.
• Use real model failures to improve rewards, training data and overall performance.

Skills

Strong programming

Quantitative skills

Experimental judgement

ML research collaboration

Tools

PyTorch

Distributed training

GPU systems

Job description

Stealth AI Lab in London or Paris (Hybrid) is seeking a Member of Technical Staff – Post-training / RL to improve models after their initial training. You will advance reinforcement learning and post-training methods while strengthening the systems that run large-scale experiments.

You’ll work across both learning algorithms and the infrastructure, from RL experiments to GPU profiling, identifying bottlenecks and ensuring system changes do not alter how the model learns.