Sr Machine Learning Engineer- Computer Vision
Cox Automotive operates Manheim, the largest wholesale vehicle auction network in the US. Between our mobile apps and imaging tunnels we see more than 10,000 vehicles and roughly 20 million images every week. That imagery is one of the largest and most diverse vehicle image catalogs in the world and is the raw material for this role. We are looking for a Senior Machine Learning Engineer to join the team automating damage detection for our auction and mobile use cases. As part of that team, you will build computer vision models for vehicle damage detection, classification and segmentation. Your models will run in production on mobile devices and auction sites across the country. They will directly affect how vehicles are valued, described and sold. This role covers the entire ML lifecycle. You will draw on our extensive catalog of vehicle information in addition to raw imagery. Based on business needs you will identify and mine new datasets, work with our 3rd party labeling team to refine them, select architectures and train proof-of concept/updated models before incorporating them into our production pipelines. You will have the opportunity to see your work progress from early R&D to production. WHAT YOU'LL DO
- Design, train and ship damage detection and segmentation models from dataset curation through deployment.
- Contribute to technical direction on model architecture, including CNNs & transformers.
- Leverage LLMs, VLMs & agentic workflows to streamline dataset mining & collection.
- Partner with our annotation teams to build the datasets that make these models work.
- Deploy models to production on server & mobile in collaboration with other teams.
- Help set the technical bar for the team’s code, experiments, and reproducibility.
- Occasional travel to attend meetings, conferences or production facilities may be required.
WHO YOU ARE MINIMUM QUALIFICATIONS
- One of the following: Bachelors with 4+ years of relevant industry experience or, MS with 2+ years or, PhD with 1+ year or, 16 years of industry experience with no degree. Degrees should be in CS, Engineering, Mathematics, or a related field.
- Minimum 2 years of experience in machine learning with a focus in Computer Vision
- Proven ML model development experience in detection, segmentation, and/or classification.
- Clear technical communication. You will be explaining trade-offs to product, engineering, and business stakeholders regularly.
- Comfort across the full stack of an ML system, including data, training & evaluation.
- Strong hands-on experience with OpenCV & NumPy for image processing and data preparation using classical CV algorithms.
PREFERRED
- C++ for performance-critical paths.
- Mobile deployment experience for Android and/or iOS.
- Multi-view geometry, Structure-from-Motion, or 3D reconstruction background.
- Machine vision camera and hardware experience.
- Familiarity with AI coding assistants, including their benefits and pitfalls.
LOGISTICS
- open to US remote- You can be based anywhere in the US excluding California or New York.
- Applicants must currently be authorized to work in the United States for any employer without current or future sponsorship. No OPT, CPT, STEM/OPT or visa sponsorship now or in future.