About the job
You’re an engineer who is excited to work on cutting-edge software products and solutions using state-of-the-art computer vision and deep learning. You have a solid foundation in areas like detection, classification, segmentation, or tracking—whether through previous roles, internships, or research—and you’re eager to apply those skills in an impactful, production-focused environment. You’re curious, motivated, and ready to learn from experienced teammates. You enjoy solving challenging technical problems, asking thoughtful questions, and collaborating with others to build high-quality software. You’re excited about contributing to the perception stack for self-driving vehicles and learning what it means to build technology for safety-critical, open-world applications.
Responsibilities
Contribute to the design, development, and improvement of perception components that support downstream modules within the autonomy system.
Help analyze perception system performance to identify areas for improvement and participate in efforts to address them.
Work with teammates to explore creative approaches to “long-tail” challenges—for example, experimenting with synthetic data, data mining techniques, or new model architectures.
Depending on your background and interests, you may also help optimize and deploy models to the vehicle, ensuring they operate within the constraints of our onboard hardware and meet our functional requirements and interface specifications.
Interface with systems and safety engineers, test engineers, and data analysts to ensure appropriate requirements, test coverage, and performance metrics
Qualifications
Minimum
Master's or Ph.D. in Machine Learning, Computer Science, Robotics, or a related field; or equivalent industry experience
Solid understanding of fundamental deep learning concepts and computer vision techniques
Experience building, training, or evaluating neural networks
Proficiency in Python and familiarity with libraries like PyTorch or similar
Exposure to software engineering fundamentals—version control, code reviews, testing, and collaborative development
Clear communication skills and willingness to ask questions, share ideas, and work with others
Preferred
Previous experience with sensor fusion and/or previous exposure to the AV industry
Experience shipping a “real” product and balancing ongoing support with next-generation innovation
Exposure to safety-critical products or components
Publications in relevant conferences (CVPR, ICML, NeurIPS, etc.)
Strong programming skills in C++ and/or CUDA programming
Experience with TensorRT and model quantization