Research engineering physics

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

This role sits on the team that builds and owns the RL training system: the system that trains our production models and that researchers across Anthropic run their experiments on. The team works closely with research teams across the company on the science and engineering of making RL work at scale.

As a Research Engineer on the team, you'll work at the center of RL at Anthropic. You'll have a direct view of how RL training behaves at the frontier because the system you own sits underneath both production and research runs. ou willl use it with collaborators across research teams to understand what is working, what is fragile, and where the next improvements are.

Build, own, and improve the core RL training system that serves Anthropic's production and research runs

Work across the stack (orchestration, environments, training, inference, evaluation) wherever the system needs it

Study how RL training behaves at scale and contribute to the research that improves it, in collaboration with teams across Anthropic

Implement new training methods as stable, fast, well-tested code

Improve the speed and efficiency of RL training and evaluation through profiling, optimization, and benchmarking

Proficiency in Python and experience working in, debugging, and improving a large ML codebase

Experience with large-scale machine learning training (reinforcement learning, pretraining, or post-training) or the systems that support it

Experience with at least one modern ML framework (JAX, PyTorch, or similar)

Ability to balance research exploration with engineering implementation

Experience with reinforcement learning for large language models, in research, production, or both

Experience studying training at scale: scaling behavior, training dynamics, or method development on large models

Experience with large-scale distributed training systems

Familiarity with LLM architectures and training methodologies

Experience working close to a frontier training run

Experience profiling and optimizing the performance of ML workloads

Experience with Rust or C++

Enjoy pair programming (we love to pair!)

For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.

Bachelor’s degree or an equivalent combination of education, training, and/or experience

Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience

Location-based hybrid policy: Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.

We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process.