TITLE: Sr. Geometric Computer Vision Engineer

ENVIRONMENT: Robotics, Healthcare, Defense

LOCATION: Remote                 Must be able to work PT time zone

COMPENSATION RANGE:  $155,000.00 – 200,000.00    DOQ

DEGREE REQUIREMENTS:  Bachelors Degree in Computer Science or related field

CITIZENSHIP:  Must be a U.S. Citizen or Green Card Holder and able to work for any U.S. Employer

EXPERIENCE LEVEL: 3 – 10 years’ experience

NUMBER OF POSITIONS AVAILABLE: 3

POSITION SUMMARY:

We enable machines to understand their surroundings in 3D and in real time using only passive sensors like cameras and IMUs. Our VIDAS™ technology takes video from automotive-grade cameras and outputs a dense, semantic 3D representation of the world that vehicles and robots can use to navigate their environment. VIDAS is a fully redundant alternative to LiDAR and radar. We have customers in automotive, agriculture, healthcare, and defense.

We’re a team with a mission to teach machines to see.

• We are developing a passive perception system for machines, focusing on vehicles, using video from conventional cameras to produce a dense 3D semantic representation of the world. • The company primarily works in the defense sector due to the preference for non-emitting sensors like cameras over lidar or radar, to avoid detection. • We aim to expand its applications beyond defense to sectors like automotive, agricultural robotics, and healthcare. • The company is looking for computer vision engineers with strong generalist skills, proficiency in C++, a solid math background, and experience in linear algebra and 3D vision tasks. • We do not require candidates to have a PhD or master's degree, focusing instead on practical experience and coding proficiency. • The company is remote-first, offering flexibility that may be more suitable for mid-career professionals. • We aim to double the team size over the next 12-18 months, maintaining a strong culture with low turnover and commitment to remote work.

What You’ll Do:

• Design and advance algorithms for pose estimation, SLAM, Visual-Inertial Odometry (VIO), and 3D reconstruction
• Build and tune navigation filters including EKF and other classical state estimation approaches
• Own sensor fusion pipelines that combine IMU and camera data in lidar-free setups
• Develop and maintain multi-view geometry and camera calibration systems
• Drive real-time perception solutions for autonomy and robotics applications
• Analyze algorithm performance and failure modes, and translate findings into concrete improvements
• Help grow and mentor a team of similarly qualified engineers

Tech stack:

SLAM, 3D pose estimation