Applied Researcher - Agentic RL

Highlights

• Build RL for agents that reason over long horizons, use tools and coordinate.
• Turn live workflows into tasks, environments, rewards and evaluations that ship.
• Extend verifiers, multi-agent training and RL systems tested at massive scale.

What they offer

• Equity incentives
• Flexible work
• Visa sponsorship and relocation support
• Professional development budget
• Team off-sites and conference attendance

Ideal candidate

An experimentally rigorous builder who thrives in ambiguity and loves turning messy real-world workflows into reliable learning systems. Motivated by open research, reusable systems, and working directly with users and partners.

Requirements

• Hands-on experience with RL training, scalable ML systems, agent environments or evaluation
• Experience building and debugging model-training, post-training or agent experimental loops
• Strong experimental judgment with meaningful baselines and clear failure attribution
• Strong Python and ability to build artifacts others can run and extend
• Comfort owning ambiguous problems and keeping partners current