Computer Vision Engineer

Join a fast-moving team building real-time vision systems that power advanced tracking and simulation technology. In this role, you will design and implement computer vision solutions that track objects and motion using high-speed, multi-camera data in a hardware-integrated environment.

What You’ll Do

• Develop real-time algorithms for object detection, tracking, pose estimation, and motion analysis

• Process high-frame-rate, multi-camera data to generate accurate 3D trajectories and impact insights

• Collaborate with hardware, firmware, and simulation teams to integrate vision pipelines into embedded and desktop systems

• Optimize performance using multithreading, SIMD, and GPU acceleration

• Apply camera calibration, stereo vision, and sensor fusion for precise spatial modeling

• Prototype new concepts, evaluate sensors, and support field testing

• Write clean, testable code with unit and integration testing

• Document algorithms, workflows, and data pipelines

• Support ML workflows including dataset versioning, experiment tracking, and deployment (Azure ML)

• Maintain MLOps tools (e.g., CVAT, training pipelines, evaluation workflows)

Required Qualifications

• Bachelor’s or Master’s in Computer Science, Computer Engineering, Electrical Engineering, or related field

• 3+ years of computer vision experience in real-time, product-focused environments

• Strong Python skills with OpenCV or similar libraries

• Solid understanding of camera geometry, calibration, and lens distortion correction

• Experience with multi-camera systems, stereo vision, or 3D reconstruction

• Knowledge of tracking techniques (optical flow, Kalman filters, background subtraction, deep learning)

• Experience with real-time optimization, parallel processing, or embedded CV deployment

Preferred Qualifications

• C++, PyTorch, or TensorFlow experience

• GPU programming (CUDA/OpenGL)

• Embedded systems or real-time video pipelines

• MATLAB or ROS exposure

• Azure ML (workspaces, compute, experiment tracking)

• Docker and containerized ML workflows

• Azure ML DevOps pipelines for automated training and deployment