Embedded Computer Vision Engineer
Ultralytics16 hours ago
Madrid, SpainSenior
Responsibilities
- Build and maintain model export and inference integrations from conversion through on-device support.
- Optimize and benchmark YOLO models on embedded hardware while balancing latency, memory, and accuracy.
- Debug conversion and INT8 quantization accuracy issues across models, runtimes, drivers, and devices.
- Set up, configure, flash, and validate deployments on embedded boards and development kits.
- Own technical integrations and engineering relationships with silicon and hardware partners, including AMD, Google, and Nvidia platforms.
- Lead partner engineering syncs and collaborate with compiler teams to support new YOLO architectures.
- Maintain hardware CI on self-hosted and partner-hosted devices and maintain deployment Docker images.
- Write integration guides, benchmark documentation, developer content, live sessions, and event demos.
- Support developers, customers, partners, and the sales team through GitHub and the community forum.
Requirements
- Strong machine learning or computer vision fundamentals, including understanding of YOLO models.
- Strong Python skills and working experience with PyTorch and ONNX.
- Hands-on experience with TensorRT, OpenVINO, ONNX Runtime, or a vendor NPU SDK.
- Experience with INT8 quantization, calibration, and debugging accuracy loss after model conversion.
- Hands-on experience with NVIDIA Jetson, Raspberry Pi, or NPU development boards.
- Experience flashing, configuring, and debugging deployments on constrained hardware.
- Comfort with Linux, Docker, and Python dependency management across platforms.
- Strong software engineering practices, including clean code, Git pull requests, and code review.
- Clear written English for technical documentation and communication.
- Senior-level experience owning technical integrations end to end with minimal oversight.
- Direct silicon-vendor or hardware-partner experience is preferred.
- Experience across multiple embedded and edge ecosystems is preferred.
- C++ experience, including model deployment on microcontrollers, is preferred.
- Experience running CI on self-hosted hardware runners is preferred.
- Open-source contributions, developer ecosystem experience, international collaboration, and willingness to travel to industry events are preferred.
Benefits
- Competitive salary and equity packages are offered, with compensation based on experience and contribution.
- The role is on-site in Madrid, with legal authorization to work in the country of application required.
- Flexible working hours and generous time off, including 24 vacation days, a birthday day off, and local holidays.
- Dedicated learning and development budget.
- Brand-new Apple MacBook Air or Pro, Apple Studio Display, and AirPods Pro 3.
- Opportunity to work on high-impact computer vision AI technology used across millions of devices.
About Ultralytics
Ultralytics builds computer-vision software centered on the Ultralytics YOLO family of real-time object detection models and supporting tools. Its business includes the Ultralytics HUB SaaS for dataset management, training, and deployment, along with open-source libraries, enterprise support, and commercial licensing. Founded in 2022 and headquartered in London, the privately held company raised a $30M Series A and focuses on helping developers and enterprises build and ship vision AI applications.