Member of Technical Staff - RL Environments
Toronto-founded enterprise AI company building foundation models, agentic AI, enterprise search, and private deployment products.
About Cohere
Cohere provides enterprise-focused AI models and end-to-end products, including North for agentic workplace AI, Compass for enterprise search, and models for generation and retrieval. It supports private, VPC, and on-premises deployment options.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build realistic reinforcement-learning environments for enterprise AI agents. You will create tasks, data, tool implementations, and verifiers; train and evaluate agents; identify capability gaps; and improve environments and agents. You will also work with external vendors and automate performance measurement during evaluation and training.
Requirements
- Agent engineering
- Agent optimization for industry use cases
- Agent trajectory analysis
- Agent capability evaluation
- Verifier implementation
- Reward design
- Annotation workflow design
- Data quality verification
- Synthetic data pipeline development
- Reinforcement learning training
Responsibilities
- Build reinforcement-learning environments for different agent capabilities and industries
- Train and evaluate agents in reinforcement-learning environments
- Integrate tasks, data, tool implementations, and verifiers
- Identify and address agent-performance gaps
- Work with external vendors to create high-quality environments
- Build tools to validate task, data, and verifier quality
- Automate discovery and measurement of model capability gaps
Benefits
- Weekly lunch stipend of $75/£75 or local-currency equivalent
- Health and dental benefits
- Mental health budget
- RRSP matching
- 401K
- Pension Scheme
- Parental leave top-up for up to six months
- Arts and culture benefit
- Fitness and wellness benefit
- Workspace improvement credit
- Education and learning stipend
- Six weeks of paid vacation
- Remote travel budget to other offices
- Annual company offsite
- Daily lunch program for office-based employees
- Snacks for office-based employees
- Community and social events for office-based employees
- Co-working benefit
- $500 home office stipend