Software Engineer, Perception/ML/CV

About Us
Agtonomy is a hybrid autonomy and tele-assist service platform that turns tractors and other equipment into autonomous machines. A robust sensor suite and custom software stack enable remote modes of operation with a higher margin of safety than conventional equipment. Agtonomy, through its OEM partners, will address both local agriculture skilled labor shortages and broader land maintenance operations, including wildfire prevention through land clearing.

About the role
We are looking for enthusiastic software engineers to join our Autonomy team. You will be responsible for the perception, ML, and CV software of new and existing autonomous vehicle systems through the entire product lifecycle. You will coordinate with other hardware, software, program management, and business teams to design, implement, and iterate on solutions. This position will be in our South San Francisco office with our testing grounds in Sonoma County.

What you’ll be doing:

• Apply first principles, applied theory and machine learning to solve challenging perception problems for autonomous systems (e.g. object detection, semantic segmentation, instance segmentation, dense depth, optical flow, tracking, etc.)
• Refine and optimize models for low-latency on embedded hardware
• Characterize and quantify the performance of the vision systems
• Research, prototype, and experiment with various sensors, algorithms and approaches
• Architect, design, and implement software applications, infrastructure, and tools
• Write performant, well-tested software, improve code quality through code and design reviews

What you’ll bring:

• Strong proficiency in C++11 (or newer) development for resource constrained embedded systems
• 5+ years of experience in software development for problems involving state of the art computer vision, machine learning and robotic perception techniques
• Experience handling large datasets efficiently
• Experience curating synthetic and real-world image datasets
• Experience building algorithms for various hardware sensors (eg, LiDAR, camera, radar, etc.)
• Strong mathematical skills and understanding of probabilistic techniques
• Ability to thrive in a fast-moving, collaborative, small team environment with little supervision
• Excellent analytical, communication, and documentation skills with demonstrated ability to collaborate with interdisciplinary stakeholders
• Passion for sustainable energy and electric vehicle development

What makes you a strong fit:

• Experience with real-time sensor fusion, and 3D data representations (pointclouds, meshes, etc.)
• Experience with parallel processing using hardware building blocks (CUDA, DLAs, etc.)
• Experience building and expanding ML model architectures
• Experience with compute constrained pipelines and architectures, optimizing architectures to explore the accuracy vs. compute tradeoff
• Master’s or PhD in Robotics, Computer Science, Computer Engineering, Electrical Engineering, related field or equivalent industry experience