Member of Technical Staff — RL & Agentic Model Training

Embedding VC • San Francisco, CA

3d • Onsite

About The Position

Moonlake is hiring a Member of Technical Staff to lead reinforcement learning infrastructure and agentic model post-training. The role works closely with Qi and the research team to improve large vision-language and code-generating agents through fine-tuning, reinforcement learning, trajectory data, and scalable evaluation. It brings model-training expertise to Moonlake’s work in 3D and world-building, helping systematically improve agent performance and prepare for larger-scale RL across digital and physical environments.

The position calls for a full-stack researcher and engineer who understands the complete training system and can judge when training is necessary, which methods are likely to work, and what not to pursue. The person will build training systems that help agents understand complex requests, reason across vision and language, write and execute code, operate tools, build interactive worlds, and recover from mistakes.

Moonlake is an AI company developing interactive world models and simulation infrastructure for robotics, embodied AI, and interactive applications. The team is based on-site in San Francisco.

Requirements

• 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.

Nice To Haves

• Experience at a frontier AI lab or organization operating large-scale training systems.
• Experience with code-model post-training or autonomous coding agents.
• Experience with multimodal models, robotics, simulation, or embodied AI.
• Experience designing verifiable rewards or outcome-based training systems.
• Experience scaling RL workloads across large GPU clusters.

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.
• Build Moonlake’s core post-training and RL infrastructure, create scalable systems for learning from agent trajectories, deliver measurable improvements in agent quality and task completion, and establish a reliable foundation for larger-scale agent and embodied-model training.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed