Software Engineer, Perception Scaling Evaluation

The Perception team at Waymo builds technology that powers the Waymo Driver. Our software allows the Waymo Driver to perceive the world around it, make the right decision for every situation, and deliver people safely to their destinations. We conduct research to address real-world problems and collaborate with research teams at Alphabet.

We have access to millions of miles of driving data from a diverse set of sensors, enabling software engineers like you to develop multi-modal models and techniques at scale.

Our mission is to build a stable foundation for a high-level Perception pipeline and the overall self-driving system. We act as the crucial interface between Waymo's hardware teams and the rest of the self-driving engineering organization, defining sensor requirements, providing critical feedback to hardware teams, and abstracting away system complexities.

The Sensor Health team's job is to make sure that sensors "just work" for the entire self-driving car software stack. We make sure that all sensors are properly calibrated and consistently monitored at all times. We are often the firsts to algorithmically process data from next-generation sensors on next-generation vehicle platforms and work closely with both hardware and software teams to provide the best possible sensor data from our many sensors perfectly aligned to our upstream customers.

To this end, we develop sensor data alignment and calibration algorithms, a growing sensor health backend, and deploy our systems both into the Waymo Driver and our log processing backend.

In this hybrid role, you will report to a Technical Lead Manager.

- Dive deep into the Waymo Driver's perception stack and build a deep understanding of its capabilities in various driving conditions

- Help set the perception development direction to allow the stack to scale to new driving environments, platforms, and sensors

- Collaborate across world-class engineering teams to influence the roadmap for next-generation perception technology

- Architect high-scale, mission-critical automation and evaluation frameworks that establish the "ultimate truth" for the safety, performance, and reliability of the Waymo Driver

- Innovate simulation tools for advanced sensor emulation, rigorously testing vehicle performance against complex impairments and edge-case faults

- Support sign-off process for all stages of sensing system development and software releases. Present results at milestone sign-off reviews

- BS in Computer Science, Robotics, similar technical field of study, or equivalent practical experience

- 2+ years of experience in industrial AI applications involving the creation, maintenance, and evaluation of ML products

- Experience developing and conducting eval for large ML software systems

- Strong experience programming in C++ with robust and efficient code

- MS or PhD in Computer Science, Robotics, similar technical field of study, or equivalent practical experience with at least 2 years of industry experience

- Experience with autonomous vehicles (L4) or ADAS systems (L2/L3)