RESEARCHER, AGENTS FOR AUTOMATED DISCOVERY

What you'll do

• Improve agent planning, task decomposition, tool use, context management, and failure recovery; develop multi-agent coordination methods.
• Build evaluation frameworks and run rigorous experiments on open-ended agent capabilities.
• Co-design agent architectures with engineering teammates, ship research into production, and share findings to help shape team direction.

What they ask for

• Strong ML research track record focused on agents, RL, LLMs, planning, tool use, or multi-agent systems.
• 5+ years of hands-on research experience in industry or academia.
• Experience designing and running experiments end-to-end at scale and building evaluation frameworks for capabilities that are not easily benchmarked.
• Published research at NeurIPS, ICML, ICLR, COLM, RLC, or comparable venues.

Nice to have

• PhD in ML, statistics, CS, or an adjacent field.
• Research or contributions involving agentic systems, tool use, long-horizon planning, multi-agent coordination, self-improvement, reasoning methods, agentic fine-tuning, or open-source agentic ML.

Tools

ML, RL, LLMs

AI focus

Research and develop autonomous multi-agent systems for automated ML research and discovery, including planning, coordination, evaluation, and recursive self-improvement.