Staff Autonomy Engineer, Perception

About the role

Kodiak AI, Inc. (Nasdaq: KDK), founded in 2018, is a leader in Physical AI, developing driverless technology that powers machines that move. Its Kodiak Driver is a vehicle-agnostic autonomous driving system that combines AI-powered software with modular hardware. Today it operates in long-haul trucking, industrial trucking, and defense. In 2024, Kodiak launched commercial Driver-as-a-Service operations with no one in the cab, and plans to launch driverless long-haul service between Dallas and Houston by the end of 2026.

Kodiak has partnered with many of the biggest names in freight, including Bosch for scaled hardware production, AWS, and leading customers including Atlas Energy Solutions, IKEA, Bridgestone, Werner Enterprises, C.R. England, Roehl Transport, and General Dynamics Land Systems.

We are seeking a Staff Autonomy Perception Engineer to join our Perception Engineering team. In this role, you will use your expertise in state estimation & multi object tracking to shape the perception stack as we scale, incorporating and developing state of the art algorithms and techniques. You’ll leverage advanced Artificial Intelligence (AI) models and techniques to deploy and scale safe autonomous perception systems. If you're passionate about how robots perceive and understand the world at scale, this role is for you.

What You'll Do

- Define and lead the technical direction for learned scene estimation within the Kodiak Driver

- Architect and implement principled approaches for fusing information across multiple modalities: camera, radar, lidar, thermal, and IMU

- Lead improvements to multi-target tracking including track initiation, measurement-to-track association, and track state maintenance — with a focus on reliability in the hardest real-world conditions

- Develop novel algorithms that incorporate noisy, incomplete measurements into a robust foundational understanding of the world

- Build the tooling, metrics, and visualization infrastructure that lets the team move faster and evaluate progress rigorously

- Set a high technical standard across the Perception team through design reviews, code reviews, and mentorship

- Partner with teams across autonomy to ensure perception performance translates into system-wide safety and reliability

What You'll Bring

- BS or MS with at least 8 years of industry experience, or PhD with at least 5 years, building and deploying state estimation and sensor fusion systems

- Deep domain expertise across sensor fusion, state estimation, Kalman filtering, particle filtering, and multi-object tracking

- Strong experience with deep learning and learned scene estimation — you know when to use classical methods and when learned approaches win

- Exceptional C++ skills and a track record of writing highly maintainable, production-quality code in high-reliability systems

- The ability to define metrics, design rigorous evaluations, and use data to make principled engineering decisions