Location: Fairport, NY – Hybrid | Employment Type: Full Time
About the Role
We’re looking for a Machine Learning Software Engineer to build and ship computer vision and deep learning systems for real-world robotics and autonomous perception. You’ll work in Python and C++ to develop production-grade software that turns multi-sensor data into reliable, real-time intelligence using modern ML and imaging pipelines.
What You’ll Accomplish
- Build and improve detection, segmentation, and monocular metric depth estimation models
- Develop 3D multi-object tracking (data association, motion models, track lifecycle) that turns per-frame detections into stable, ID-consistent tracks
- Design RGB–thermal fusion architectures for robust multi-modal perception
- Develop production software in Python/C++ using PyTorch and OpenCV
- Turn product requirements into scalable, real-time technical solutions
- Build and optimize imaging and GPU-accelerated processing pipelines
- Curate and prepare training datasets from raw multi-sensor data streams
- Develop end-to-end autonomy/perception software components
- Design and implement autonomous perception algorithms for real-time perception and decision-making systems.
- Develop and optimize ADAS features supporting vehicle safety and driver assistance capabilities.
- Build failure-case mining pipelines (hard examples, label issues, data gaps)
- Generate derived data products (depth maps, BEV tensors, object states, fused views)
- Work in an Agile team shipping iterative improvements to production systems
Role Level & Scope
- Individual contributor role
What We’re Looking For
Required
- 3+ years of software development experience in Python and C++
- Strong experience with PyTorch and/or TensorFlow
- Ability to translate complex technical concepts into clear, accessible language for non- technical stakeholders.
- Hands-on computer vision experience (detection, classification, 3D vision, point clouds, etc.)
- Experience with multi-object tracking (Kalman/EKF filtering, data association, track management; 3D/BEV tracking a plus)
- Familiarity with perception evaluation metrics (e.g., mAP for detection, MOTA/MOTP/IDF1 for tracking)
- Strong OpenCV and image processing skills
- Experience with multi-modal data (RGB, thermal, LiDAR, radar, IMU, etc.)
- Familiarity with dataset building (labeling, schema design, QA, taxonomy)
- Understanding of camera geometry, calibration, and imaging fundamentals
- Experience working in Agile environments
- Ability to translate ambiguous product needs into working systems
Preferred
- MS in ML, Computer Vision, Robotics, or related field
- Experience with GPU optimization or edge deployment constraints
- Familiarity with lightweight models for real-time systems
- Experience with MATLAB or similar tooling
- Valid driver’s license or ability to obtain one within the first 6 months of employment.
- Exposure to robotics/autonomy systems or sensor fusion
- Experience with ROS1/ROS2 or similar frameworks
- Experience building systems that scale across environments or customers
- Technical leadership or ownership experience in production systems
Compensation Range
$100k – $140k annually, based on experience, qualifications, and geographic location, plus applicable benefits.
Opens an email to hr@owlai.us with the role title filled in. Attach your CV and tell us briefly why this one.