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

The role

The Research Engineer / Scientist will develop and train advanced LLMs and VLMs, including multimodal architectures. You will research training methods for instruction following and tool use while designing data pipelines and training systems.

What you will do

• 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
• Stay current with advancements in LLMs, VLMs, and related fields

Required qualifications

• Experience training and improving large language models at different scales in distributed computing settings
• Strong programming skills in Python, Rust, or similar
• Strong software engineering fundamentals building performant and reliable systems
• Proficient in deep learning frameworks (Pytorch, JAX, TensorFlow)
• Ability to work on different layers of the stack from low-level training backends to ML/RL algorithmic design
• Experience training LLMs/VLMs with techniques such as SFT, DPO, RLHF/RLVR, reward modelling, offline RL, distillation, etc.
• Experience with offline and online reinforcement learning in or outside of the context of language models

Nice to have

• Publications in top-tier AI conferences (e.g., NeurIPS, ICML, CVPR, ACL, ICCV, AAMAS, ...)
• Advanced degree (PhD or MSc) in a relevant field (e.g., ML, DL, NLP, CV)
• Experience with large-scale distributed training and inference (multi-node, large models, MoE, parallelism strategies, etc)
• Experience training models for computer use or other multi-turn and/or multimodal agentic settings
• Extensive experience with reinforcement learning with sparse rewards
• Experience with multi-domain training, data mixture design, curriculum learning, model merging, distillation

Benefits

• Join the exciting journey of shaping the future of AI
• Collaborate with a fun, dynamic and multicultural team
• Highly competitive salary
• Opportunities for professional growth, continuous learning, and career development

About the company

H exists to push the boundaries of superintelligence with agentic AI. The Models team builds the foundational models that power agentic technology.