Applied AI Researcher, Agent Systems and Evaluation

The Robot Age; Mountain View, Northern (CA, KY); Hybrid; USD 140,000 - 210,000; Full time

Job summary

Nuro is hiring an applied AI researcher focused on agent systems and evaluation. The work sits around the research and measurement loop for autonomous driving systems, with emphasis on how agent behavior is tested, compared, and improved.

For an impact-focused role, the emphasis is on evaluation-driven design—turning insights into system improvements and real-world readiness across simulation, logs, and autonomy cases.

Qualifications

• Background in applied AI, robotics, ML, or autonomy research.
• Experience evaluating agentic or autonomous systems.
• Ability to turn ambiguous behavior questions into measurable experiments.
• Strong collaboration with engineering and research teams.

Responsibilities

• Develop evaluation approaches for autonomous driving agent behavior.
• Work with model, autonomy, and product teams to turn research findings into system improvements.
• Analyze agent performance across simulation, logged data, and real-world autonomy cases.
• Help define the metrics and experiments that guide Nuro's applied AI roadmap.

Skills

Applied AI

Robotics

Machine Learning

Autonomy research

Evaluation experiments

Collaboration

Job description

What the role actually is

Nuro is hiring an applied AI researcher focused on agent systems and evaluation. The work sits around the research and measurement loop for autonomous driving systems, with emphasis on how agent behavior is tested, compared, and improved.

For The Robot Age, the interesting part is the evaluation angle. Better robotics products depend on knowing whether an autonomous system behaves well enough in the situations people actually encounter.

What you would work on

• Develop evaluation approaches for autonomous driving agent behavior
• Work with model, autonomy, and product teams to turn research findings into system improvements
• Analyze agent performance across simulation, logged data, and real-world autonomy cases
• Help define the metrics and experiments that guide Nuro's applied AI roadmap

What they are asking for

• Applied AI, robotics, machine learning, or autonomy research background
• Experience evaluating agentic or autonomous systems
• Ability to turn ambiguous behavior questions into measurable experiments
• Strong collaboration with engineering and research teams

Why this one is worth a look

Evaluation is becoming one of the central product problems in robotics. This role is not about publishing a standalone model; it is about helping an autonomy company understand whether its agents are ready for the real world.