Evaluation Engineer

About the role

About Maven

Maven Robotics designs, builds, and deploys intelligent robotics for logistics and manufacturing. Maven is building the first general-purpose robotics system for industrial work. Our mission is to activate autonomous labor at scale and build toward infinitely elastic industrial capacity. We’re a team of engineers, researchers, and operators who have spent our careers working on the hardest problems in AI, robotics, engineering, and autonomous systems. We work at the intersection of advanced research and real-world engineering, turning ideas into prototypes and deployed systems.

At Maven, we build around the realities of industrial work. The robots are designed from first principles for complex physical environments and rigorous commercial standards. They master real tasks that deliver immediate impact, industrial-grade reliability, and intelligence that compounds at scale. We’re growing an ambitious team of people who think in systems, move quickly, and are builders at heart.

About the Role

As a Robotics Evaluation Engineer at Maven Robotics, you will build the systems that measure, diagnose, and improve robot policy performance across simulation and real robots. You will own the core evaluation infrastructure that enables our AI team to rigorously compare models, understand failure modes, measure generalization and reliability, and make better decisions about data, training, and deployment.

You will work closely with robot learning researchers and engineers across simulation, perception, controls, data, and infrastructure to define task success, build reproducible evaluation frameworks, automate testing, and develop the tools needed to understand why robot policies succeed or fail.

What You’ll Do

- Own the architecture, implementation, and evolution of Maven’s robot learning evaluation framework across simulation and real robots

- Define task specifications, success criteria, failure taxonomies, evaluation metrics, and benchmark protocols for manipulation policies

- Build automated systems for comparing models, detecting regressions, running large-scale evaluations, and generating clear performance reports

- Develop simulation environments, task scenarios, and procedural variations used for policy evaluation

- Build reproducible real-robot evaluation workflows that minimize manual supervision and produce statistically meaningful results

- Measure and improve the relationship between simulated and real-world policy performance

- Build tools for replaying, visualizing, and diagnosing policy failures across simulation and physical robots

- Work closely with robot learning researchers to identify whether failures originate from the model, data, perception, controls, calibration, simulation, hardware, or long-horizon execution

What We’re Looking For

- Significant experience building robotics evaluation, simulation, testing, or benchmarking systems.