Staff Engineer, RL & Post-Training for Multimodal Agents

Embedding; San Francisco (CA); On-site; USD 190,000 - 270,000; Full time

Job summary

Moonlake is building the frontier of interactive world models for robotics and embodied AI. We develop infrastructure to learn, simulate, and evaluate in realistic virtual environments before acting in the real world.

We are hiring a Member of Technical Staff to lead reinforcement learning infrastructure and model post-training, collaborating with Qi and the research team to scale RL across both digital and physical environments.

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.

Skills

RL infrastructure

Large-scale training

Python

PyTorch

JAX

System design

Research judgment

Education

PhD/MS in CS/ML

Tools

PyTorch

JAX

Distributed systems

Job description

Moonlake is building the frontier of interactive world models for robotics and embodied AI. We develop infrastructure to learn, simulate, and evaluate in realistic virtual environments before acting in the real world.

We are hiring a Member of Technical Staff to lead reinforcement learning infrastructure and model post-training, collaborating with Qi and the research team to scale RL across both digital and physical environments.