Cohere6 days ago
Специалист по технической инженерии - RL Environments
Salary not specified
Полная занятостьУдалёнка
Responsibilities
- 01Build new RL environments targeting different agentic capabilities and industry areas
- 02Train and evaluate agents in those environments
- 03Make all the pieces work together: tasks, data, tool implementations, and verifiers
- 04Work across modeling and product to identify gaps in agent performance, and improve both the agents and the environments
- 05Work with external vendors to create high-quality, expert-built RL environments, and build tools to ensure high task, data, and verifier quality
- 06Automate the discovery of model capability gaps, and systematically measure agent performance during evals and training
Requirements
- 01You have engineered agents and optimized them for specific industry use cases
- 02You have spent dozens of hours reviewing agent trajectories to pinpoint exact failure points and fix them with model training or harness engineering
- 03You obsess over measuring agentic capabilities and turning that into a repeatable process
- 04You have had many debates about what a good outcome from an AI agent should look like, you translated that into verifier implementations and tuned the reward designs
- 05You have designed and run annotation workflows to surface insights into agent performance and verify data quality
- 06You have built synthetic data pipelines to scale eval and training efforts
- 07You use agents yourself in your daily work, and have stories about how you improved your setup to 10x your productivity
- 08A plus: you have experience with training with RL: scaling, troubleshooting and tuning the environments
What we offer
- 01Remote or office-based work (Toronto, London, New York City, San Francisco, Montreal, Paris, Berlin, Seoul)
- 02Weekly lunch stipend of $75/£75 or equivalent in your local currency
- 03Full health and dental benefits, including a separate budget for mental health
- 04RRSP matching, 401K, Pension Scheme
- 05100% Parental Leave top-up for up to 6 months, for either parent
- 06Annual enrichment benefits: Arts & culture, fitness/wellness, quality time, and a workspace improvement credit
- 07Education & learning stipend for conferences, courses, and coaching
- 086 weeks of paid vacation (30 working days)
- 09Budget for traveling to other offices if you are remote, plus an annual company offsite
- 10Daily lunch program, plenty of snacks, and regular community and social events (for office workers)
- 11Co-working benefit for those not near an office
- 12$500 home office stipend