Staff Research Scientist - Post-Training for Agents

📋 Description

• Drive research in agent post-training and reinforcement learning, shaping the technical direction
• Own research problems end to end, from framing the question through experimentation, model
• Design and advance reinforcement learning approaches, post-training methods, and training loops for
• Build simulated environments, synthetic data generation approaches, and evaluation frameworks that
• Raise the technical bar across the team by reviewing research directions, mentoring researchers and
• Collaborate with cross-functional teams across Research, Product, and Engineering to translate

🎯 Requirements

• PhD in Computer Science, Machine Learning, or a related field, or equivalent experience, with deep
• Driven technically ambitious research at meaningful scale as an individual contributor, whether in
• Extensive hands-on experience designing and implementing reinforcement learning systems, agent
• Track record of research impact through influential publications, significant model or system
• Ability to set technical direction through influence rather than authority, and mentorship
• Desire to stay deeply hands-on in research for the long term, and ability to communicate complex

🎁 Benefits

• Competitive salary and equity package
• May include variable compensation
• Healthcare, dental, parental planning, and mental health benefits
• 401(k) plan and match
• Paid time off
• Fitness reimbursements