Requirements:

• Experience in building RL environments
• Ability to train and evaluate agents
• Strong problem-solving skills across tasks, data, tool implementations, and verifiers
• Collaboration with modeling and product teams for agent and environment improvements
• Experience in working with external vendors for expert-built RL environments
• Proficiency in automating discovery of model capability gaps

Qualifications:

• Engineering agents for specific industry use cases
• Reviewing agent trajectories to improve performance
• Measuring agentic capabilities and creating repeatable processes
• Translating good outcomes into verifier implementations and reward designs
• Designing annotation workflows for agent performance insights
• Building synthetic data pipelines for evaluation and training
• Experience with RL training and scaling

What You'll Be Doing:

• Building new RL environments for different agentic capabilities and industries
• Training and evaluating agents within these environments
• Ensuring seamless integration of tasks, data, tool implementations, and verifiers
• Identifying gaps in agent performance and improving agents and environments
• Collaborating with external vendors to create high-quality RL environments
• Automating the discovery of model capability gaps and measuring agent performance

Perks and Benefits:

• Weekly lunch stipend
• Full health, dental benefits, and mental health budget
• RRSP matching, 401K, and Pension Scheme
• Parental Leave top-up for up to 6 months
• Annual enrichment benefits including arts & culture, fitness/wellness
• Education & learning stipend
• 6 weeks of paid vacation
• Travel budget for visiting other offices
• Remote-friendly work environment
• Home office setup stipend