Member of Technical Staff — Agent Post-Training
San Francisco, CAFull-timePosted 2mo ago
About the role
Moonlake is building AI infrastructure for interactive 3D world simulations, focusing on learning, evaluating, and interacting with rich virtual environments for robotics, embodied AI, and related applications. This role leads reinforcement learning infrastructure and model post-training to improve multimodal agents and prepare for large-scale RL across digital and physical environments.
Responsibilities
- Build RL and post-training pipelines for multimodal, vision-language, and code-generating agents
- Develop infrastructure for supervised fine-tuning, preference optimization, reward modeling, and reinforcement learning
- Create systems for collecting, filtering, replaying, and learning from agent trajectories
- Design rewards, verifiers, and evaluations for long-horizon agent tasks
- Improve agents’ ability to plan, write and execute code, use tools, recover from errors, and complete complex workflows
- Scale distributed training and high-throughput rollout generation across multi-GPU environments
- Improve training reliability, reproducibility, observability, and cost efficiency
- Help define Moonlake’s long-term strategy for agent, robotics, and embodied-model training
Qualifications
- Real-world experience training large language, vision-language, multimodal, or code models
- Strong experience in reinforcement learning, post-training, or large-scale fine-tuning
- Experience building distributed training or high-throughput inference systems
- Familiarity with supervised fine-tuning, preference optimization, reward modeling, and agentic RL
- Experience with code-generation agents, long-horizon evaluation, or tool-using systems
- Strong Python skills and experience with PyTorch, JAX, or similar frameworks
- Ability to work across data, models, environments, rewards, evaluation, and infrastructure
- Strong research judgment and a bias toward building reliable systems
Skills
Required:Reinforcement learningMultimodal model trainingDistributed trainingPythonPyTorch/JAX
Last updated Jul 29, 2026. Interested? Apply on the company site.
About Moonlake
We’re building AI so anyone can create interactive worlds.
Moonlake AI is a team of Stanford CS PhDs, Math Olympiad and ACM ICPC medalists, industry veterans from NVIDIA, Meta, Epic Games, and Netflix, with the mission of democratizing studio-grade interactive worlds.
AIinteractive worldsdemocratizing creative technology
More open roles at Moonlake
- Member of Technical Staff — Post-Training Infrastructure4d agoSan Francisco, CA · Engineering & Research
- Member of Technical Staff — RL & Agentic Model Training4w agoSan Francisco, CA · Engineering & Research
- Head of Design2mo agoSan Francisco, CA · Engineering & Research
- Head of People Operations5mo agoSan Francisco, CA · Operations
- Member of Technical Staff - Head of Robotics10mo agoSan Francisco, CA · Engineering & Research