- Auburn Hills, Michigan, United States
- Full-time · Associate
- 3+ years
The Computer Vision Algorithm Engineer role focused on ADAS perception turns camera video feeds (image frames) into a clear understanding of the vehicle’s surroundings. The work spans concept through serial production: design and simulate algorithms, analyze and replay data, build and test classical and deep learning models, and optimize for real-time execution on production ECUs.
Responsibilities
- Develop (design, implement, optimize) conventional image processing algorithms for automotive embedded serial production projects.
- Design, develop/tune, and optimize deep learning models for ADAS computer vision features (e.g., pruning, quantization) and improve computational performance.
- Plan and execute experiments to assess deep learning model effectiveness, compare architectures, and validate results through rigorous component/bench testing.
- Strong knowledge of various camera models; lens distortion correction; homograph and projective transformations mathematical techniques
- Analyze large datasets to extract insights, refine models, and improve overall performance and robustness.
Requirements
- Master’s degree in computer engineering
- Software Engineering
- Electrical Engineering
- Computer Science
- Nice to have: Python