Research Engineer / Scientist, Post-training & Reinforcement Learning - London

Job summary

Responsibilities

Our work spans the development of Large Language Models (LLMs) and Vision-Language Models (VLMs), enabling agents to perceive, understand, and act within complex environments. We own the entire pipeline including synthetic data generation, environment design, mid-training, supervised fine-tuning…

• Develop and train advanced LLMs and VLMs, including multimodal architectures
• Research and implement training methods for enhanced capabilities like instruction following and tool use
• Design and optimize data pipelines and training systems for large-scale distributed training
• Collaborate with cross-functional teams to integrate models into agentic AI systems
• Evaluate model performance and communicate findings to stakeholders

What they're looking for

• You have strong programming skills in Python, Rust, or similar; and strong software engineering fundamentals building performant and reliable systems.
• Proficient in deep learning frameworks (Pytorch, JAX, TensorFlow).
• You can work on different layers of the stack from low-level training backends, data ingestion to ML/RL algorithmic design and implementation.
• You know when and where to be rigorous and slower versus when to break and iterate quickly.
• You have trained LLMs/VLMs with techniques such as SFT, DPO, RLHF/RLVR, reward modelling, offline RL, distillation, etc.

Tech stack

• Python
• Rust
• PyTorch
• JAX
• TensorFlow
• Node.js