At XDOF, we’re at an inflection point. Frontier labs are racing to build general-purpose robots, and high-quality training data is the bottleneck. We’re building the foundation behind the foundation models – the data collection systems, operational capability, exabyte-scale data warehouse, and software toolchain – to help our partners drive the field forward.

We’re looking for a Robotics Infrastructure Engineer to build the product and infrastructure that lets us and our partners deploy and evaluate learned robotis policies on real hardware. Examples of things you might work on are: deploying VLAs, imitation learning models, and DAgger workflows onto embodied systems, building the evaluation frameworks that measure how they perform, and shipping the product surfaces that make this accessible to partners.

What You’ll Do

Robotics Infrastructure engineers own the systems that get models running on robots and measure how well they work. Sample projects include:

deploying and running learned robot policies (VLAs, imitation learning, DAgger) on real hardware, including inference setup, on-robot tuning, and failure diagnosis

designing and building evaluation frameworks that benchmark policy performance on physical robots, with metric definition, result aggregation, and partner-facing reporting

building the product that lets partners configure, launch, and monitor evaluation runs and model deployments

building orchestration systems that schedule evaluation runs and model deployments across robot stations

integrating LLMs and foundation models into robot workflows for task specification, error recovery, or high-level planning

containerizing and packaging robot-side software stacks so new stations and deployments can be brought online quickly and consistently

bridging on-robot systems with cloud-side compute, storage, and orchestration

About You

Baseline skills

bachelor’s degree or equivalent experience in Computer Science, Robotics, or a related field

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 containerization (Docker) and building reproducible deployment workflows

You might be a good fit if you

have deployed imitation learning, reinforcement learning, or VLA policies on physical robots

have built evaluation or benchmarking infrastructure for robotic systems or ML models

have experience with DAgger or other interactive data collection and policy refinement loops

have experience with ROS/ROS2 and understand robotics middleware at the integration level

have built product features or partner-facing tools on top of technical infrastructure

are very comfortable working in 0→1 environments

are mission-driven and passionate about robotics: work at XDOF is fast-paced and constant. We hope you love what you’re going to be doing, because you’ll be doing a lot of it!