2 months ago
London, United KingdomSenior
Responsibilities
- Build new reinforcement-learning environments for different agent capabilities and industry areas.
- Train and evaluate AI agents within reinforcement-learning environments.
- Integrate tasks, data, tool implementations, and verifiers.
- Collaborate across modeling and product teams to identify agent-performance gaps and improve agents and environments.
- Work with external vendors to create expert-built reinforcement-learning environments.
- Build tools to ensure task, data, and verifier quality.
- Automate discovery of model capability gaps and systematically measure agent performance during evaluations and training.
Requirements
- Experience engineering agents and optimizing them for specific industry use cases.
- Extensive hands-on experience reviewing agent trajectories to identify failure points and resolving them through model training or harness engineering.
- Experience measuring agent capabilities and creating repeatable evaluation processes.
- Experience defining desired agent outcomes, implementing verifiers, and tuning reward designs.
- Experience designing and running annotation workflows to analyze agent performance and verify data quality.
- Experience building synthetic data pipelines to scale evaluation and training efforts.
- Regular use of agents with demonstrated improvements to personal workflows.
- Experience with reinforcement-learning training, including scaling, troubleshooting, and tuning environments, is a plus.
Benefits
- Weekly lunch stipend of $75/£75 or equivalent in local currency.
- Full health and dental benefits, including a separate mental health budget.
- RRSP matching, 401K, and Pension Scheme.
- 100% parental leave top-up for up to 6 months for either parent.
- Annual enrichment benefits covering arts and culture, fitness and wellness, quality time, and workspace improvement.
- Education and learning stipend for conferences, courses, and coaching.
- Six weeks of paid vacation, or 30 working days.
- Travel budget for remote employees to visit other offices and an annual company offsite.
- Remote-friendly work arrangement with offices in Toronto, London, New York City, San Francisco, Montreal, Paris, Berlin, and Seoul.
- Co-working benefit for employees not near an office.
- Daily lunch program, snacks, and community and social events for office-based employees.
- $500 home office stipend.
Categories
AI Research
About Cohere
Cohere builds large language models and an enterprise AI platform that companies use for search, summarization, and workflow automation, delivered via API or private deployments. Founded in 2019 and headquartered in Toronto, it focuses on multilingual models, data controls, and options to run across major clouds or on-premises. The business is privately held and serves security- and compliance-sensitive organizations.