Research Engineer, Benchmarking, Robotics, DeepMind

Google•Mountain View, CA
•$147,000 - $210,000

About The Position

At Google, research-focused Software Engineers are embedded throughout the company to set up large-scale tests and deploy promising ideas quickly and broadly. They create experiments and prototype implementations, design new architectures, and work on real-world problems while staying connected to the research community through collaboration with universities and paper publication. Google DeepMind’s mission is to bring advanced AI into the physical realm by building generalist robots that perceive, reason, and act naturally alongside humans. The Research Engineer will manage practical challenges in benchmarking robotics foundation models, understand how these models work and where they fall short, and design evaluation protocols, tools, and frameworks that extract meaningful signals from physical policy execution. The role builds infrastructure to help engineering teams improve models and give leadership a data-driven understanding of technological readiness.

Requirements

  • Bachelor’s degree in Computer Science, Robotics, or equivalent practical experience.
  • At least 2 years of experience with machine learning tools and algorithms, specifically deploying Large Language Models (LLMs), Vision Language Models (VLMs), and deep learning models.
  • At least 2 years of experience working in and with robotics.
  • Experience in a technical role such as software engineering, AI/ML engineering, or solutions architecture.
  • Experience with Python and modern AI-assisted development tools to accelerate prototyping.

Nice To Haves

  • Experience with ROS/ROS2 or on-device deployment constraints such as Jetson or TPU.
  • Experience managing multimodal datasets or time-series telemetry data, or building automated pipelines for hardware-in-the-loop testing.
  • Familiarity with the operational realities of modern vision-language-action (VLA) models or behavior-cloning policies and common pitfalls such as task overfitting.
  • A deep-seated interest in the future of embodied AI and a desire to build the testing bedrock for robotics development.

Responsibilities

  • Design, implement, and maintain scalable frameworks for evaluating robot policies through offline open-loop testing and real-world hardware evaluations.
  • Partner with researchers to design benchmark content that maximizes evaluation signal and stress-tests model capabilities.
  • Build diagnostic and visualization tools to help the team identify the root causes of policy failures and track performance regressions.
  • Establish evaluation criteria for model releases and own the stability and benchmarking of models slated for critical demos.
  • Develop ways to make real-world hardware evaluation faster, more reproducible, and less reliant on manual human intervention.

Benefits

  • 15% bonus target
  • Equity
  • Benefits
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service