Software Engineer II, Computer Vision

Scythe Robotics - Longmont, CO

Full-time - Mid Level

Remote - Longmont, CO

Professional, Scientific, and Technical Services

About the position

Scythe is seeking a highly skilled Software Engineer with a strong foundation in traditional image processing techniques, sensor fusion, and integrating machine learning solutions. As part of the Perception team, you will assist in building out the future of off-road, real-time robot perception. The ideal candidate will have strong programming proficiency in languages such as C++ and Python. Experience with Rust and familiarity with Neural Networks is a plus. This role is critical to Scythe, as it enables our autonomous mower, M.52, to operate in ever-expanding environments and provide a reliable operational experience to our customers. We expect you to be broadly experienced, to be able to 'see around corners', to thrive in a fast-paced, self-managed engineering environment, and to be a collaborative, low-ego teammate who helps Scythe realize its big mission.

Responsibilities

• Design, develop, and maintain robot SW, including: Robot localization, camera calibration, sensor fusion (camera, radar, GPS, ultrasonics, lidar), obstacle detection and tracking, and depth estimation.
• Optimize algorithms for computational efficiency and scalability in real-time or resource-constrained environments.
• Implement efficient data extraction and processing pipelines to support machine learning workflows, ensuring data quality and accuracy.
• Create and enhance testing frameworks for evaluating our Perception pipeline.
• Maintain comprehensive documentation for SW and processes to ensure clarity and facilitate knowledge sharing.
• Stay updated with the latest advancements in computer vision, machine learning, data platforms, and programming languages to incorporate new technologies and methodologies.

Requirements

• Mathematical concepts relevant to the tasks of visual-inertial odometry, sensor fusion, and 3D reconstruction: linear algebra, matrix math, non-linear optimization, uncertainty propagation, rotation parameterizations, isometries, etc.
• Proficiency in compiled programming languages such as C++, Rust, or Go.
• Kalman filter and nonlinear variants (EKF, UKF) and bundle adjustment.
• GNSS+IMU sensor fusion for localization.
• Vision-based localization (camera models, visual odometry, SLAM).

Nice-to-haves

• Worked with robots or other resource-constrained platforms.
• Experience working with camera, lidar, and radar data in a robotics application.
• Experience with machine learning libraries and frameworks such as Pytorch.
• Experience working with vision-based machine learning models.
• CUDA development to parallelize algorithms.

Benefits

• Competitive salary and equity compensation.
• Fully-sponsored medical, vision, and dental insurance, including 75% funded dependent coverage.
• 401(k) retirement plan (non-matching today).
• Flexible paid time-off and remote work to let you do your best work where and when you want.
• Highly collaborative learning culture where personal freedom, growth, and responsibility are valued.
• An opportunity to have an incredible positive impact on the world.