Machine Learning Research Lead, RL Agents

What you'll do

• Lead research on reinforcement learning and post-training for agentic capabilities including tool calling, coding, and multi-step tasks.
• Build and own synthetic data pipelines and interactive environments to create training curricula for capable agents.
• Develop and manage the codebases and infrastructure required for core RL research efforts.
• Manage and mentor a small team of senior researchers while shaping their shared research direction.
• Perform hands-on technical work including running experiments, writing code, and solving complex engineering problems.
• Optimize post-training methods to ensure compatibility with on-device and hybrid compute constraints.
• Publish original research in top venues and engage with the broader academic community.

What we're looking for

• PhD in machine learning or a related field, or equivalent research experience.
• 7-10+ years of research experience beyond a PhD in industry or as an academic research lead.
• Strong track record in RL and/or post-training of large models through publications, open-source contributions, or shipped systems.
• Leadership experience setting research direction over multiple years and directing the work of others.
• Experience owning ML infrastructure, frameworks, and codebases including open-source research frameworks or environment suites.
• Strong engineering skills with comfort working hands-on in large training codebases.
• Experience taking research from idea to product or production impact (preferred).
• Familiarity with efficiency-aware modeling, such as small models, MoE, quantization, or hardware-aware design (preferred).