Member of Technical Staff — RL & Agentic Model Training

The role

You will lead reinforcement learning infrastructure and agentic model post-training. You will work to improve large vision-language and code-generating agents through fine-tuning, reinforcement learning, trajectory data, and scalable evaluation.

What you will do

• 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 Moonlakes long-term strategy for agent, robotics, and embodied-model training

Required 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

Nice to have

• 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

About the company

Moonlake is building the frontier of interactive world models that generate, simulate, and reason over 3D environments. The team has raised $50M in seed funding from NVIDIA Ventures, Threshold Ventures, AIX Ventures, and notable angels.