Research Engineer - Data and Evaluation

Role overview

Create tasks, interactive environments, and evaluation methods that help train AI models through reinforcement learning and reveal their real capabilities. You’ll work with researchers to investigate failures, following issues from task implementation through scoring and measurement.

Responsibilities - Design challenging evaluations for coding systems and agents that handle long-horizon tasks. - Build executable environments with realistic task setups and clearly defined success conditions. - Develop and test scoring logic and verification methods; investigate reward hacking and misleading measures of progress. - Trace failures through model outputs and evaluation harness code to identify their causes. - Contribute in areas such as data generation, environments and rewards, or evaluation systems, according to your expertise.

Requirements

The available source does not provide a full qualifications list. It highlights experience in at least one of data generation, environment and reward design, or evaluation systems; experience across every area is not expected.

Benefits and work setup - Full-time role with remote work or in-person work in San Francisco. - Stated cash compensation range of $150,000–$350,000, including equity incentives. - Visa sponsorship and relocation assistance are available for international candidates. - Quarterly team off-sites, hackathons, conferences, and learning opportunities.