Staff Research Scientist - Post-Training for Agents

Tech Stack

Responsibilities

• Drive research in agent post-training and reinforcement learning, shaping technical direction grounded in observability and security
• Design and advance reinforcement learning systems, training loops, and simulated environments for autonomous agents
• Build synthetic data generation pipelines and evaluation frameworks enabling scalable agent training
• Mentor other researchers and engineers, elevating standards for experimental rigor across the team
• Collaborate with product and engineering teams to translate research achievements into scalable Datadog product capabilities

Benefits

• 401k
• Equity
• Gym Membership
• Health Insurance
• Learning Budget

Culture

Requirements