Lead Perception Engineer

About this role

About ATI: Automated Tire (ATI) is on a mission to reinvent tire changing and wheel balancing using cutting-edge robotics. We are transforming a process that hasn’t fundamentally changed in decades into an automated, high-performance system built for the future of automotive service. Founded by experienced entrepreneurs and backed by leading players across the automotive and tire industries, ATI is building technology that will redefine how cars are serviced. Our team combines deep robotics expertise with real world deployment, moving fast from prototype to production and scaling solutions directly in the field. This role offers an exciting opportunity to work at the forefront of robotics and industrial automation, applying cutting-edge AI and ML techniques to develop advanced vision control systems. If you are a perception or computer vision engineer with a passion for solving complex automation challenges, we encourage you to apply and become a key part of our innovative team. Position Overview: We are looking for a highly skilled and experienced Lead Perception Engineer with expertise leading a team of engineers solving difficult robotic perception challenges using both classical and machine learning (ML) approaches. The ideal candidate will have hands-on experience with developing solutions end to end, including evaluation of the problem, sensor selection, leading software development and evaluating the solution in the real world to ensure success. Key Responsibilities: Lead Technical Execution: Guide a team of engineers through the full development lifecycle, from initial concept, hardware selection and algorithm design to field deployment and maintenance. You will lead the team in the following work: Integrate classical and ML image processing algorithms for classification, depth sensing, and 3D reconstruction. Select the optimal sensors (e.g., LIDARs, time-of-flight cameras, stereo vision) for various applications. Create AI and ML models to enhance object detection, classification, and tracking capabilities. Utilize deep learning techniques to improve system accuracy and efficiency. Conduct extensive testing, validation, and calibration to ensure system accuracy and reliability. System Design: Design and maintain high-throughput perception pipelines, ensuring low latency and high reliability in real-time environments. Active Debugging: Take a "hands-on" approach to identifying and resolving bottlenecks or failures in the perception stack, including hardware-software integration issues. Willingness to spend time on the shop floor or in the field to debug hardware-in-the-loop failures. Code Quality & Mentorship: Drive high standards for code reviews, architectural design, and documentation while mentoring junior team members. Collaboration: Work with cross-functional teams, including mechanical, system, mechatronic, software and software quality assurance engineers, and domain experts to ensure solutions are aligned and integrated with product goals. Requirements 8–10 years of professional software engineering experience in robotics, computer vision, or a closely related field. At least 2–3 years of experience in a formal or informal leadership capacity, such as a Team Lead, Tech Lead, or Mentor, with a track record of guiding technical projects and junior engineers. Strong foundation in robotics fundamentals, including coordinate transforms, sensor calibration, perception pipeline design, and system architecture. Proven ability to perform hands-on, low-level debugging and systematic troubleshooting of complex robotic systems in real-world environments. Expert-level proficiency in Python, C++ and/or Rust with a focus on writing production-grade, well-tested code for autonomous systems. Demonstrated experience designing, implementing, testing, and optimizing vision solutions for robotic or automation applications. Experience in building ML pipelines and optimizing/productizing ML models. Proficiency in AI/ML frameworks (e.g. PyTorch) and computer vision libraries (e.g., OpenCV, PCL, Open3D, CUDA). Familiarity with various depth sensing modalities (e.g., LiDAR, stereo vision, time-of-flight) and sensor fusion. Excellent problem-solving skills, attention to detail, and ability to work in a dynamic environment. Preferred Qualifications: Master’s or PhD degree in Computer Science, Computer Vision, Machine Learning, or a related field. Experience developing within the ROS2 ecosystem.