Member of Technical Staff – RL Environments

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Develop new reinforcement learning environments aimed at various agentic capabilities and industry sectors.

• Train and assess agents within these environments.

• Integrate tasks, data, tool implementations, and verification processes.

• Collaborate with modeling and product teams to pinpoint gaps in agent performance.

• Enhance both agents and their operational environments.

• Partner with external vendors to produce high-quality, expert-designed RL environments.

• Create tools to guarantee the quality of tasks, data, and verifiers.

• Automate the identification of model capability gaps.

• Methodically evaluate agent performance during training and assessments.

⛳️ Requirements

• Proven experience in engineering agents and optimizing them for specific industry applications.

• Extensive hours spent reviewing agent trajectories to pinpoint exact failure points and addressing them through model training or harness engineering.

• Strong emphasis on measuring agentic capabilities and establishing repeatable evaluation processes.

• Experience in defining desired outcomes for AI agents, implementing verifiers, and refining reward structures.

• Familiarity with designing and executing annotation workflows to extract agent-performance insights and ensure data quality.

• Background in building synthetic data pipelines to enhance evaluation and training initiatives.

• Regular utilization of AI agents in everyday tasks, with examples of productivity improvements.

• Experience with reinforcement learning training, including scaling, troubleshooting, and tuning environments is advantageous.

🏝️ Benefits

• A weekly lunch stipend of $75/£75 or equivalent in your local currency for lunch.

• Comprehensive health and dental coverage, with a separate budget allocated for mental health.

• RRSP matching, 401K, and Pension Scheme.

• 100% Parental Leave top-up for up to 6 months, applicable to either parent.

• Annual enrichment benefits for arts & culture, fitness/wellness, quality time, and workspace improvement credits.

• Education and learning stipend for conferences, courses, and coaching.

• Six weeks of paid vacation (30 working days).

• Budget for travel to other offices for remote employees.

• Annual company offsite.

• Daily lunch program, abundant snacks, and regular community and social events for onsite employees.

• Co-working benefits for those located away from an office.

• $500 home office stipend.