The Domain Scaling team at Anthropic works to make Claude world‑class at real‑world knowledge work in domains such as finance, healthcare, and legal. This role blends applied research and data sourcing, focusing on end‑to‑end reinforcement learning environment creation, vendor management, data strategy, and measuring the impact of data changes on model performance.
Research Engineer, Domain Scaling at Anthropic
Hybrid - San Francisco, CA, New York City, NY, Seattle, WA, United States
More jobs at AnthropicSalary
USD 350,000 - 850,000
Requirements
Skills
- Experience with fine-tuning large language models for specific domains or real-world use cases
- Experience with reinforcement learning, reward design, or training data curation for large language models
- Comfortable managing technical vendor relationships and iterating quickly on feedback
- Ability to read datasets to understand them and spot issues
- Strong cross‑functional collaboration skills
- Passion for making AI more useful and accessible across different industries
- Excitement about a role combining applied research and hands‑on data work
- Experience training production machine learning systems (preferred)
- Experience designing evaluation metrics or benchmarks for large language models (preferred)
- Domain expertise in a vertical where making models more useful is desired (preferred)
- Experience working with external vendors or technical partners (preferred)
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 reinforcement learning environments for high‑value tasks
- Develop and improve QA frameworks to catch reward hacking and ensure environment quality
- Run generalization experiments to measure how data strategy changes improve model capabilities
- Partner with other reinforcement learning research teams and product teams to translate capability goals into training environments and evaluations
Technologies
Reinforcement LearningLarge Language ModelsReward DesignRL TrainingQA FrameworksData Pipelines
See if your resume is ready for this job
See how our AI can optimize your resume and improve your chances for this role.