Research Engineer, RL Engineering

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. About the role Reinforcement learning (RL) is how Claude learns to reason, write code, and act autonomously over long horizons. 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. Key responsibilities 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 Make the system easier for researchers to build on, through clean abstractions, clear APIs, and automated testing Debug hard problems across the stack, from a run that has quietly drifted to a distributed systems failure that only shows up at scale Communicate results clearly, in writing and in discussion Minimum qualifications 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 design controlled experiments and reach conclusions you and others can trust Ability to balance research exploration with engineering implementation Strong written and verbal communication skills Care about the societal impacts of your work and are committed to developing safe and beneficial systems Preferred qualifications 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 RL environments, evaluations, or sandboxed code execution Experience with Rust or C++ Enjoy pair programming (we love to pair!) The annual compensation range for this role is listed below. 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. Annual Salary: $500,000 — $850,000 USD Logistics Minimum education: 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 Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices. 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. We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. 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 think this makes representation even more important, and we strive to include a range of diverse perspectives on our team. Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings. How we're different 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. As such, we greatly value communication skills. 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. Come work with us! Anthropic is a public benefit corporation headquartered in San Francisco. 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.