Research Engineer / Scientist, Post-training & Reinforcement Learning - London
H Company· Research
Hybrid (Hybrid London)Full-timePosted 6mo ago
About the role
Research Engineer / Scientist focused on post-training and reinforcement learning for agentic AI, with hybrid work in London. Responsibilities span developing/training LLMs and VLMs, improving instruction following and tool use, and building scalable training pipelines, with collaboration across teams to deploy agentic systems.
Responsibilities
- 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
Qualifications
- Strong programming skills in Python, Rust, or similar; strong software engineering fundamentals
- Proficient in deep learning frameworks (PyTorch, JAX, TensorFlow)
- Experience training LLMs/VLMs with techniques such as SFT, DPO, RLHF/RLVR, reward modelling, offline RL, distillation
- Experience with offline and online reinforcement learning in or outside of language models
- Ability to work across training backends, data ingestion, ML/RL algorithm design and implementation
- Strong research mindset with distributed computing experience
Skills
Required:PythonPyTorch / JAX / TensorFlowDistributed trainingRL from RLHF / RLVR / offline RL
Nice to have:Rust
Benefits
- Highly competitive salary
- Opportunities for professional growth and continuous learning
- Collaborative, multicultural environment
Last updated Oct 8, 2026. Interested? Apply on the company site.
About H Company
H is an AI Research Lab and Product Company
H is an AI Research Lab and Product Company
AIProductResearchfrontier-labsheadline-ai-europe-100-2026liquid-ai-recruiting-target
More open roles at H Company
- Founder's Associate - CEO office4d agoHybrid (Hybrid Paris) · Operations
- Content Manager4d agoHybrid (Hybrid Paris), Hybrid (Hybrid London) · GTM
- Digital Manager4d agoHybrid (Hybrid Paris), Hybrid (Hybrid London) · GTM
- Technical Lead, Observability - London1w agoHybrid (Hybrid London), Hybrid (Hybrid Paris) · Engineering
- Technical Lead, Observability - Paris1w agoHybrid (Hybrid Paris), Hybrid (Hybrid London) · Engineering