Cox Automotive is seeking to solve the problem of vehicle damage detection and segmentation using machine learning models, specifically computer vision, to drive the next generation of vehicle damage analysis.
Requirements
- Expertise with Python and relevant ML libraries such as PyTorch, OpenCV & CoreML for datacenter and mobile.
- Proficiency with AI coding assistants such as Github Copilot, Claude Code and GPT 5 to improve developer productivity.
- Experience with annotation tools, dataset management, and versioning.
- Proven experience in image segmentation, object detection or related subjects.
- C++ proficiency
- Model deployment for mobile & web platforms
- Dataset development using third party annotation firms
Responsibilities
- Lead the design, implementation, and optimization of computer vision algorithms for automated damage analysis.
- Develop, test and refine deep learning models such as CNNs & transformers for damage detection, classification and segmentation.
- Develop & curate datasets leveraging Cox Automotive's annotation partners and massive catalog of vehicle imagery and condition reports.
- Collaborate with data engineers and software developers to integrate models into scalable, production-grade systems.
- Research and prototype novel approaches leveraging the latest advancements in computer vision and machine learning.
- Communicate results, challenges, and opportunities clearly with cross-functional teams and stakeholders.
- Contribute to setting team standards for code quality and reproducibility
Other
- Master's or Ph.D. in Computer Science, Engineering, Mathematics, or a related field or 16 years experience
- Must live or be willing to relocate to Atlanta GA or Austin TX and work in a hybrid office setting weekly
- Applicants must currently be authorized to work in the United States for any employer without current or future sponsorship.
- Ability to work independently and in collaborative team environments.
- Strong analytical, problem-solving, and communication skills.
