About this role
EAIGLE is a computer vision AI platform helping enterprises in supply chain and logistics turn vision data into security, transportation, and operational outcomes. Our solutions include AVAC™, automated vehicle access control at the retailer's gate, and YardSight™, real-time monitoring of loading docks and truck parking availability across the yard. The platform combines on-premise computer vision components with Azure cloud services, and is deployed today at Fortune 100 and 500 companies.
The Role
We're looking for a Computer Vision Researcher to take AI solutions for image and video understanding from research through to production. You'll own problems end to end: framing them, experimenting, building and training models, evaluating rigorously, optimizing for real-world constraints, and shipping to cloud and edge environments.
This is a role for someone who is comfortable moving between a paper and a production incident in the same week, and who is willing to pick up whatever technology the problem requires.
What You'll Do
• Research, adapt, and deploy state-of-the-art computer vision and deep learning methods for our products.
• Design, train, fine-tune, and evaluate models across detection, tracking, segmentation, OCR, and related vision tasks.
• Build the data pipelines behind the models — collection, annotation, augmentation, and preprocessing at scale.
• Optimize models for accuracy, latency, memory, and cost, and deploy them to cloud and edge environments.
• Define evaluation metrics, benchmark rigorously, and monitor deployed models to drive the next iteration.
• Document your findings and designs clearly, and contribute to publications, patents, or open source where it makes sense.
What We're Looking For
• Master's or PhD in Computer Science, AI, Electrical Engineering, Mathematics, or a related technical field.
• Substantial research or professional experience in computer vision and deep learning.
• Depth in 3D camera geometry and motion. This is central to what we do, and we want someone who has genuinely worked in this space — 3D tracking, structure from motion, visual SLAM, multi-view geometry, camera calibration and pose estimation, stereo or depth estimation, or closely adjacent problems.
• Strong Python skills, with hands-on experience in PyTorch and/or TensorFlow and OpenCV.
• Experience taking models from experiment to production.
• Comfort working across Linux and Windows, with Git and modern engineering practices.
• Strong analytical and communication skills, and the self-direction to work through ambiguous problems.
Nice to Have
• Experience with modern architectures and frameworks such as Vision Transformers, YOLO, SAM, CLIP, diffusion models, or vision-language and multimodal systems.
• Inference optimization and acceleration experience — quantization, pruning, distillation, ONNX, TensorRT, OpenVINO, CUDA.
• Edge AI or embedded deployment experience.
• Familiarity with Azure or another major cloud platform, and with MLOps tooling and ML pipelines.
• Experience with containerized deployment with Docker
• C++ alongside Python.
• Publications at recognized vision or AI venues, or contributions to open-source vision projects.