Full-Stack Engineer for RL Data Platforms

Anthropic; New York (NY); Hybrid; USD 300,000 - 405,000; Full time

Job summary

Anthropic seeks a Full-Stack Software Engineer in RL to build the platforms, tools, and interfaces that power environment creation, data collection, and training observability. You will own surfaces end‑to‑end from backend services to web UIs used by researchers, external vendors, and thousands of data labelers.

You will work with Python and a modern web stack, shipping polished, reliable products quickly and collaborating with RL researchers, data operations, and vendor teams.

Qualifications

• Bachelor’s degree or equivalent combination of education, training, and/or experience.
• Strong software engineering fundamentals and full‑stack range.
• Proficiency in Python and modern web stacks (React, TypeScript).
• Track record of shipping systems that solve hard problems with impact.

Responsibilities

• Build and extend web platforms for RL environment creation, management, and quality review.
• Develop vendor-facing interfaces and tooling for external partners.
• Design platforms for human data collection at scale with QA and feedback.
• Create dashboards and observability UIs for real‑time insights.
• Build backend services and APIs connecting tools and training infra.
• Develop data generation pipelines across languages and difficulty levels.
• Automate onboarding and documentation for vendors and internal users.
• Collaborate with RL researchers, data operations, and vendor teams.

Skills

Strong software engineering

Python

React

TypeScript

Education

Bachelor's degree or equivalent

Tools

Docker

AWS/GCP

CI/CD pipelines

Job description

Anthropic seeks a Full-Stack Software Engineer in RL to build the platforms, tools, and interfaces that power environment creation, data collection, and training observability. You will own surfaces end‑to‑end from backend services to web UIs used by researchers, external vendors, and thousands of data labelers.

You will work with Python and a modern web stack, shipping polished, reliable products quickly and collaborating with RL researchers, data operations, and vendor teams.