Research Engineer

Role overview

Join Anthropic’s Environment Scaling team to improve the intelligence of public models for novel verticals and use cases. As a Research Engineer, you will build and iterate on reinforcement learning (RL) environments, measure their impact on model performance, and collaborate closely with domain experts.

Key missions

• Own the end-to-end creation of RL environments for new capabilities, including:
  • Identifying high-value tasks
  • Designing reward signals
• Manage technical relationships with external data vendors, including:
  • Evaluating data quality
  • Informing reward design
• Collaborate with domain experts to design:
  • Data pipelines and evaluations
  • Novel approaches for creating RL environments for high-value tasks
• Explore novel RL-environment creation methods and develop QA frameworks for evaluation quality.

Requirements

• Bachelor’s degree in a related field or equivalent experience
• Comfort managing technical vendor relationships and iterating quickly on feedback
• Strong project management and interpersonal skills
• Motivated by a mix of ML research, data operations, and project management
• Domain expertise in an area where models should become more useful
• Experience with fine-tuning large language models for specific domains or real-world use cases
• Familiarity with distributed systems and cloud infrastructure
• Experience with reinforcement learning, reward design, and/or training data curation for LLMs
• Ability to read and analyze datasets to understand them and spot issues
• Experience working with external vendors/technical partners
• Value-driven mindset focused on making AI more useful and accessible
• Experience training production ML systems

Remote / location policy

• Listed as full remote, but the posting also states a hybrid expectation: staff should be in an office at least 25% of the time (some roles may require more).