Research Engineer, Domain Scaling

Overview

Research Engineer on the Domain Scaling team, focusing on improving Claude for real-world knowledge work via applied RL environment creation, data sourcing, and impact measurement.

What you'll do

• Own end-to-end data strategy for knowledge work verticals from task sourcing through RL training.
• Manage technical relationships with external data vendors, including evaluating data quality and reward design.
• Collaborate with domain experts to design data pipelines and evaluations.
• Develop and improve QA frameworks to detect reward hacking and ensure environment quality.
• Run generalization experiments to measure how data strategy changes improve model capabilities.
• Partner with other RL research and product teams to translate capability goals into training environments and evals.

What you'll need

• Experience fine-tuning large language models for specific domains or real-world use cases.
• Experience with reinforcement learning, reward design, or training data curation for LLMs.
• Comfort managing technical vendor relationships and iterating based on feedback.
• Value reading through datasets to understand them and spot issues.
• Strong cross-functional collaboration skills.
• Interest in a role combining applied research with hands-on data work.

Details

• Hybrid work policy: expected to be in one of the offices at least 25% of the time.
• Visa sponsorship is available, with reasonable efforts if an offer is made.