justbacked
← All jobs
xdof

Member of Technical Staff, Evaluations

San Mateo Hybrid · Full-time

$180K–$300K

Venture round · $70M · 157d ago Posted 4d ago
Have your AI draft the answers and brief you on xdof→

Why join xdof?

Picture robots that learn fine motion from data collected at scale for the world's largest research labs. XDOF, a Berkeley robotics company, could become the motion layer every autonomous system is built on. Andreessen Horowitz and Thrive Capital led its $70M round, bigger than 88% of rounds at its stage, and 24 open roles, 9 in engineering, mean a team of 11 to 50 is still small enough to shape.

JustBacked's take, based on xdof's own site and its funding and hiring data.

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 model evaluation platform – to help our partners drive the field forward.

We’re looking for an Evaluations Software Engineer to build how the field measures robot intelligence. You’ll develop the benchmarks that tell our partners how their LLMs, VLAs, and WAMs actually perform on physical tasks, in simulation and on real hardware. Examples of things you might work on: designing benchmark tasks, developing our simulation pipeline, measuring how well simulation predicts real-world performance, and integrating novel research into the evaluations workflow.

What You’ll Do

Evaluations engineers own how we measure models and what we learn from it. Sample projects include:

  • designing benchmark tasks for LLMs, VLAs, and WAMs that test real robotics capabilities, from long-horizon planning to dexterous manipulation

  • building verifiers, success detectors, and progress metrics that grade episodes reliably in simulation and on real hardware

  • building harnesses that let LLMs and coding agents control robots, directly or by planning over VLAs

  • measuring how well simulation results predict real-world performance, and improving that correlation

  • fine-tuning open-source VLAs consistently so every model gets a fair baseline

  • analyzing failures across runs to find capability gaps, and turning them into targeted data collection and RL environments

  • producing partner-facing results with rigorous statistics and clear reporting

You might be a good fit if you have:

  • strong programming skills in Python or C++

  • built benchmarks, evaluation pipelines, or graders for ML models, and thought hard about what a score actually measures

  • hands-on experience with robot learning, simulation (MuJoCo, Isaac Sim, or similar), or deploying policies on real hardware

  • worked with LLM or coding agents, and can read a trace to diagnose why a model failed

  • an adversarial mindset: your first question about a metric is how it could be gamed

  • built and shipped software in fast-moving environments

Bonus points if you have:

  • contributed to robotics or agent benchmarks (e.g. LIBERO, BEHAVIOR, RoboArena, Terminal-Bench)

  • experience with RL, reward modeling, or post-training

  • worked on real2sim, system identification, or sim-to-real transfer

  • experience with statistics for evaluation, like confidence intervals and variance across runs

  • familiarity with containerized evaluation frameworks such as Harbor