Robotics Platform Engineer

XDOF • San Francisco, CA

2d

About The Position

XDOF is building data collection systems, operational capabilities, an exabyte-scale data warehouse, and a software toolchain to support partners developing general-purpose robots. The Robotics Platform Engineer builds the product and infrastructure needed to deploy and evaluate learned robot policies on real hardware. The work includes deploying vision-language-action (VLA) and imitation-learning models and DAgger workflows on embodied systems, developing evaluation frameworks, and delivering product interfaces that make these capabilities accessible to partners. The role bridges robot-side systems with cloud compute, storage, and orchestration.

Requirements

• Bachelor’s degree or equivalent experience in Computer Science, Robotics, or a related field.
• At least 3 years of industry experience in software engineering, with exposure to robotics or ML deployment.
• Strong Python skills and comfort working in Linux environments.
• Experience deploying ML models to real systems, not just training them.
• Familiarity with Docker and building reproducible deployment workflows.

Nice To Haves

• Experience deploying imitation-learning, reinforcement-learning, or VLA policies on physical robots.
• Experience building evaluation or benchmarking infrastructure for robotic systems or ML models.
• Experience with DAgger or other interactive data collection and policy-refinement loops.
• Experience with ROS/ROS2 and an understanding of robotics middleware at the integration level.
• Experience building product features or partner-facing tools on top of technical infrastructure.
• Comfort working in 0→1 environments.
• A mission-driven outlook and passion for robotics.

Responsibilities

• Deploy and run learned robot policies, including VLAs, imitation-learning models, and DAgger workflows, on real hardware; configure inference, tune systems on-robot, and diagnose failures.
• Design and build evaluation frameworks for benchmarking policy performance on physical robots, including defining metrics, aggregating results, and producing partner-facing reports.
• Build product features that let partners configure, launch, and monitor evaluation runs and model deployments.
• Build orchestration systems to schedule evaluation runs and model deployments across robot stations.
• Integrate LLMs and foundation models into robot workflows for task specification, error recovery, or high-level planning.
• Containerize and package robot-side software stacks so stations and deployments can be brought online quickly and consistently.
• Connect on-robot systems with cloud-side compute, storage, and orchestration.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level