Research Engineer (Post-Training)

Axiōma Search; Greater London; Hybrid; GBP 90,000 - 140,000; Full time

Job summary

Stealth AI Lab in London or Paris (Hybrid) is seeking a Member of Technical Staff for post-training RL work. You’ll improve models after training and enhance the systems that run experiments at scale.

You’ll explore RL methods like PPO, GRPO and SDPO, own training loops, and boost throughput, GPU utilization, and memory efficiency while debugging training vs inference differences.

Qualifications

• Strong programming and quantitative problem-solving skills.
• Hands-on experience with PyTorch and model training.
• Understanding of reinforcement learning or LLM post-training.
• 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

Programming

PyTorch

RL post-training

Distributed training

Experimental judgement

ML research & systems

Tools

vLLM

Ray

CUDA

Megatron-LM

Job description

Member of Technical Staff – Post-training / RL

Stealth AI Lab | London or Paris (Hybrid)

About

This role is about making models better after their initial training. You'll work on reinforcement learning and other post-training methods, while also improving the systems needed to run those experiments efficiently at scale.

The company is building AI systems that learn how to carry out complex work inside large organisations. They recreate real-world workflows as interactive training environments, then use those environments to train models through practice and feedback — so the models get better at completing long, multi-step tasks reliably, rather than simply generating answers.

You'll work across both the learning algorithms and the infrastructure underneath them. That means going from an RL experiment to a GPU profiler trace, finding what's limiting performance, and making sure systems improvements don't change the way the model learns.

What you\'ll do

• 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

What you\'ll need

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

Optional

• vLLM, SGLang, Ray, FSDP or Megatron-LM
• CUDA, Triton, CuTE or GPU performance optimisation

Shortlisted candidates will be contacted within 48 hours.