Research Engineer, RL Engineering

Anthropic•Seattle, WA

4d•$500,000 - $850,000•Hybrid

About The Position

As an ML Systems Engineer on our Reinforcement Learning Engineering team, you'll be responsible for the critical algorithms and infrastructure that our researchers depend on to train models. Your work will directly enable breakthroughs in AI capabilities and safety. You'll focus obsessively on improving the performance, robustness, and usability of these systems so our research can progress as quickly as possible. You're energized by the challenge of supporting and empowering our research team in the mission to build beneficial AI systems. Our finetuning researchers train our production Claude models, and internal research models, using RLHF and other related methods. Your job will be to build, maintain, and improve the algorithms and systems that these researchers use to train models. You’ll be responsible for improving the speed, reliability, and ease-of-use of these systems.

Requirements

4+ years of software engineering experience
Results-oriented, with a bias towards flexibility and impact
Ability to pick up slack, even if it goes outside your job description
Desire to learn more about machine learning research
Care about the societal impacts of your work
Bachelor’s degree or an equivalent combination of education, training, and/or experience
A field relevant to the role as demonstrated through coursework, training, or professional experience

Nice To Haves

Experience with high performance, large scale distributed systems
Experience with large scale LLM training
Experience with Python
Experience implementing LLM finetuning algorithms, such as RLHF
Enjoy working on systems and tools that make other people more productive
Enjoy pair programming
Experience profiling reinforcement learning pipelines to find opportunities for improvement
Experience building a system that regularly launches training jobs in a test environment
Experience making changes to finetuning systems to work on new model architectures
Experience building instrumentation to detect and eliminate Python GIL contention in training code
Experience diagnosing and fixing training run slowdowns
Experience implementing a stable, fast version of a new training algorithm

Responsibilities

Build, maintain, and improve the algorithms and systems that researchers use to train models.
Improve the speed, reliability, and ease-of-use of these systems.
Support and empower the research team in the mission to build beneficial AI systems.
Focus on improving the performance, robustness, and usability of systems.
Work on the critical algorithms and infrastructure that researchers depend on to train models.