Staff Research Scientist - Post-Training for Agents

What you’d do

Drive research on agent post-training and reinforcement learning, owning problems from framing through experimentation, model development, and evaluation. Build simulated environments, synthetic data pipelines, and evaluation frameworks, and mentor researchers across Research, Product, and Engineering. Found on the employer's careers page on Oct 7, 2026. Apply through the link.

You’ll need

• PhD in Computer Science, Machine Learning, or related field, or equivalent experience
• Deep expertise in reinforcement learning, AI agents, post-training, or generative modeling
• Experience designing post-training methods and training loops for agents
• Building simulated environments, synthetic data, and evaluation frameworks
• Mentoring researchers and research engineers