Polymath Labs
Member of Technical Staff - Research
$150K–$300K
San Francisco · On-site · Staff · Full-time · Posted Apr 14, 2026
About the job
Conduct research and engineering to evaluate and improve long-horizon autonomous agents through benchmarks, simulation environments, post-training, and experiments.
What you'll do
- Investigate frontier model failure modes and build rigorous benchmarks and environments for evaluating agents.
- Post-train agents to reason, plan, and act over extended time horizons; run rigorous experiments.
- Write production-quality code and publish research.
What they ask for
- Experience post-training frontier models.
- Experience shipping reliable, production-quality code.
- Track record of publications.
- Strong engineering and research fundamentals; prolific use of AI tools.
Pay
$150K – $300K (base salary)
AI focus
Research and develop safe, capable autonomous agents, including long-horizon evaluation, agent post-training, and environment design.
Model-written summary · the original posting is authoritative