Research Engineer, Domain Scaling — Real-World RL

Contentbuffer; San Francisco (CA); Hybrid; USD 170,000 - 210,000; Full time

Job summary

Anthropic is seeking a Domain Scaling role to own end-to-end RL environment creation for real-world knowledge work, from task sourcing to reward design and vendor management.

The successful candidate will collaborate with RL researchers and product teams to translate capability goals into training environments and evaluations that improve Claude's performance across domains such as finance, healthcare, and law, with a strong hands-on data component.

Qualifications

• Bachelor's degree or equivalent required.
• Experience tuning LLMs for domain-specific tasks.
• Experience with RL or reward design.

Responsibilities

• Own the data strategy for knowledge work verticals end-to-end, from task sourcing through RL training
• Manage technical relationships with external data vendors, including evaluation of data quality and reward design
• Collaborate with domain experts to design data pipelines and evaluations
• Explore novel ways of creating RL envs for high value tasks
• Develop and improve QA frameworks to catch reward hacking and ensure env quality
• Run generalization experiments to measure how data strategy changes improve model capabilities
• Partner with other RL research teams and product teams to translate capability goals into training envs and evals

Skills

Fine-tuning LLMs

Reinforcement Learning

Data Curation

Vendor Management

Cross-functional Collaboration

Education

Bachelor's degree or equivalent

Job description

Anthropic is seeking a Domain Scaling role to own end-to-end RL environment creation for real-world knowledge work, from task sourcing to reward design and vendor management.

The successful candidate will collaborate with RL researchers and product teams to translate capability goals into training environments and evaluations that improve Claude's performance across domains such as finance, healthcare, and law, with a strong hands-on data component.