Staff ML Engineer, RL & Multimodal Training

Embedding VC; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Moonlake is building the frontier of interactive world models and seeks exceptional engineers to lead reinforcement learning infrastructure and model post-training. You will work with the research team to improve large vision-language and code-generating agents through fine-tuning, RL, trajectory data, and scalable evaluation.

Moonlake already has deep expertise in 3D and world-building. This role adds model-training experience to systematically improve agent performance and prepare the company

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.

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

Skills

RL training

Post-training

Large-scale fine-tuning

Distributed training

Python

PyTorch

JAX

Multimodal models

Code-generation agents

Robotics/Embodied AI

Tools

PyTorch

JAX

Job description

Moonlake is building the frontier of interactive world models and seeks exceptional engineers to lead reinforcement learning infrastructure and model post-training. You will work with the research team to improve large vision-language and code-generating agents through fine-tuning, RL, trajectory data, and scalable evaluation.

Moonlake already has deep expertise in 3D and world-building. This role adds model-training experience to systematically improve agent performance and prepare the company