Polymath
Member of Technical Staff - Research
San Francisco. Posted 7 months ago
The role
You will work on core research problems in long-horizon evaluation, agent post-training, and environment design. You will build benchmarks, create environments, write production code, and run rigorous experiments.
What you will do
- Investigating failure modes of frontier models
- Creating rigorous benchmarks that evaluate how well frontier agents perform on complex, realistic tasks requiring long-horizon reasoning and tool use in dynamic environments
- Post-training agents that can reason, plan, and act over extended time horizons
- Publishing research
- Building benchmarks
- Creating environments
- Writing production code
- Running rigorous experiments
Required qualifications
- Strong engineering and research fundamentals
- Prolific user of AI tools
- Experience post-training frontier models
- Experience shipping reliable, production-quality code
- Track record of publications
Benefits
- Comprehensive health, dental, and vision insurance
- Free meals with the team
- Free Bay Club membership
- Commuter benefits
- 401(k)
- Unlimited PTO
- Top of the line tech
- Frequent team activities and outings
About the company
Polymath is an applied research lab focused on advancing long-horizon agent capabilities through reinforcement learning. The team works with leading model labs to push the frontier of agent capabilities.