Research Engineer / Research Scientist, RL Frontiers

Highlights

• Develop next-gen RL algorithms and scale them to frontier-scale runs.
• Own end-to-end performance of Anthropic's largest RL training runs.
• Study how RL throughput and stability evolve as models and compute scale.

What they offer

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space for collaboration

Ideal candidate

A research-driven engineer fascinated by RL at scale who loves digging from research code to hardware to explain instabilities and turn promising ideas into reliable frontier runs.

Requirements

• Deep familiarity with modern transformer language models, architecture, training dynamics and large-scale optimization
• Hands-on experience training large models in a distributed setting including data, tensor and pipeline parallelism
• Track record of original technical work in ML training or systems via research, open-source or production impact
• Ability to design rigorous experiments at scale with baselines, ablations and statistical care
• Ability to reason quantitatively about compute, memory and communication costs
• Strong programming skills in Python and JAX or PyTorch and comfort across the full stack