Full-Stack Software Engineer – Reinforcement Learning

About the role

Anthropic is looking for a Full‑Stack Software Engineer to build the platforms, tools, and interfaces that enable reinforcement‑learning environment creation, data collection, and training observability. You will own product surfaces from backend services and APIs to web UIs used by researchers, external vendors, and thousands of data labelers.

Key responsibilities

• Build and extend web platforms for RL environment creation, management, and quality review, including configuration, versioning, and validation workflows.
• Develop vendor‑facing interfaces that let external partners create, submit, and iterate on training environments with minimal friction.
• Design and implement scalable platforms for human data collection, labeling workflows, quality‑assurance systems, and feedback loops.
• Own end‑to‑end product surfaces, from backend services and APIs to the web UIs used daily by internal and external users.

Required profile

• Proven ability to take ambiguous, high‑stakes problems and ship polished, reliable products quickly.
• Experience building end‑to‑end product surfaces, including backend services and user‑facing web interfaces.
• Comfort working in a fast‑moving, iterative environment where judgment and rapid response are critical.

Required skills

What we offer

• Opportunity to impact the next generation of Claude by shaping the data and tools that train it.
• Work with a rapidly growing team of researchers, engineers, policy experts, and business leaders in AI safety.