Software Engineer, Localization

Agtonomy South San Francisco, CA 47 days ago

engineering

About Us

Agtonomy brings intelligent automation to agriculture, turf, and other demanding industries through Physical AI and software services. By partnering with trusted equipment manufacturers, we deliver factory-fit technology that transforms industrial machines into smart, efficient solutions built for safety and performance. Our team combines expertise in technology, product development, and industry knowledge to address critical challenges like labor shortages, sustainability, and productivity. We’re looking for people who want to work in a collaborative, fast-moving environment where their ideas can make a real impact.

About the Role

As a Localization Engineer on the Autonomy Team, you will be responsible for developing state estimation algorithms to help our tractors more accurately estimate their pose with respect to the local and global frames. You will work closely with perception, planning, and controls engineers on the team to design and evolve the outputs of the pose and localization systems to better serve their consumers. This role is perfect for someone who loves combining math and software, and is excited about applying their experience to make robots drive in smart ways in rugged, agricultural environments.

What You'll Do

Implementing new features to improve the stability and reliability of our local and global pose estimates.

Designing mitigation and fallback strategies for the pose estimation systems.

Creating robust online and offline sensor calibration routines that perform reliably in complex and unpredictable environments.

Researching, prototyping, and experimenting with various sensors and state-of-the-art state estimation algorithms.

Architecting, designing, and implementing software applications, as well as onboard and offboard infrastructure and tools to support those applications.

Developing portable, scalable, and fast geometry and optimization libraries.

Writing performant, well-tested software, and improving code quality of the entire Autonomy team through code and design reviews.

Validating your solutions on real vehicles in real-world scenarios.

What You'll Bring

Demonstrated experience deploying state estimation algorithms in real robots: Kalman filters, particle filters, structure from motion, visual inertial odometry, etc.

Deep understanding of the design tradeoffs involved when fusing various sensing technologies: cameras (mono and stereo), LiDAR, RADAR, GNSS, IMUs, wheel encoders, etc.

Experience implementing state estimation math effectively in software with the following libraries: Eigen, Ceres, GTSAM, etc.

Strong proficiency in modern C++ and experience writing efficient algorithms for resource-constrained embedded systems.

Ability to thrive in a fast-moving, collaborative, small team environment with lots of ownership.

Excellent analytical, communication, and documentation skills with demonstrated ability to collaborate with interdisciplinary stakeholders outside of Autonomy.

An eagerness to get your hands dirty by testing your code on real robots at real customer farms (gives “field testing” a whole new meaning!).

What Makes You a Strong Fit

Experience architecting state estimation systems from scratch and understanding the design tradeoffs when leveraging filters, pose graph optimization, etc.

Experience with state-of-the-art visual and/or lidar odometry algorithms.

Experience implementing custom factors for factor graph optimization.

Thinks/dreams in Lie algebra.

5+ years of software development experience in autonomy, robotics, or a related field.

MS or PhD in Robotics, Computer Science, Computer Engineering, Electrical Engineering, or a related field.

Passion for sustainable agriculture and electric vehicles.

Benefits:

• 100% covered medical, dental, and vision for the employee (cost plus partner, children, or

family is additional)

• Commuter Benefits

• Flexible Spending Account (FSA)

• Life Insurance