Anthropic· AI Research & Engineering· Remote-Friendly (Travel Required) | San Francisco, CA
Research Engineer, Environment Scaling
Classified Tasks (18)
Automate 0%Augment 83%Human-Only 17%
Augment (15)
AI assists, human decides
Build training environments that fuel reinforcement learning at scale
technical
Execute ML research to develop and validate training approaches for models
analytical
Perform data operations to curate, preprocess, and maintain datasets for RL environments
operational
Identify high-value tasks to include in RL training environments
analytical
Design reward signals for RL training
technical
Evaluate data quality from external vendors
analytical
Design and evaluate reward structures in collaboration with vendors
technical
Collaborate with domain experts to design data pipelines
technical
Collaborate with domain experts to design evaluations
analytical
Explore novel methods for creating RL environments for high-value tasks
creative
Develop QA frameworks to detect reward hacking and ensure environment quality
technical
Improve QA frameworks to address environment failures and reward exploitation
technical
Improve fine-tuning strategies for adapting Claude to new domains and tasks
technical
Execute fine-tuning strategies to adapt Claude to new domains and tasks
technical
Measure the impact of training environments and fine-tuning on model performance
analytical
Human-Only (3)
Requires human judgment
Manage the end-to-end creation of RL environments for new capabilities
leadership
Manage technical relationships with external data vendors
leadership
Partner with RL research and product teams to translate capability goals into training environments and evaluations
communication
Job description
About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. About the role The Environment Scaling team is a team of researchers and engineers whose goal is to improve the intelligence of our public models for novel verticals and use cases. The team builds the training environments that fuel RL at scale. This is a unique role that combines executing directly on ML research, data operations, and project management to improve our models. You'll own the end-to-end process of creating RL environments for new capabilities: identifying high-value tasks, designing reward signals, managing vendor relationships, and measuring impact on model performance. Responsibilities: Improve and execute our fine-tuning strategies for adapting Claude to new domains and tasks 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 environments for high value tasks Develop and improve QA frameworks to catch reward hacking and ensure environment quality Partner with other RL research teams and product teams to translate capability goals into training environments and evals You may be a good fit if you: Have experience with fine-tuning large language models for specific domains or real-world use cases and/or domain expertise in an area where we would like to make our models more useful. Have experience with reinforcement learning, reward design, or training data curation for LLMs Are comfortable managing technical vendor relationships and iterating quickly on feedback Find value in reading through datasets to understand them and spot issues Have strong project management and interpersonal skills Are passionate about making AI more useful and accessible across different industries Are excited about a role that includes a combination of ML research, data operations, and project management Strong candidates may also: Have experience training production ML systems Be familiar with distributed systems and cloud infrastructure Have domain expertise in an area where we would like to make our models more useful Have experience working with external vendors or technical partners The annual compensation range for this role is listed below. For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role. Annual Salary: $350,000 — $850,000 USD Logistics Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position Location-based hybrid policy: Currently, we expec