Computer Vision Engineer
About the role
We’re looking for a Computer Vision Engineer to design, build, and deploy vision models that power core parts of our product. You’ll own projects end to end, from data collection and model development through production deployment and monitoring, working closely with ML, software, and product teams.
What you’ll do
- Develop and train models for tasks such as object detection, segmentation, classification, tracking, and pose estimation
- Build and maintain data pipelines for collection, labeling, augmentation, and validation
- Optimize models for latency, memory, and accuracy across cloud and/or edge environments
- Deploy models to production and monitor performance, drift, and failure cases
- Evaluate new research and approaches and bring the useful ones into production
- Write clean, tested, maintainable code and contribute to shared tooling
What we’re looking for
- 3+ years of experience building computer vision systems, with at least one model shipped to production
- Strong Python skills; experience with PyTorch or TensorFlow
- Solid grounding in deep learning architectures (CNNs, transformers, detection/segmentation frameworks)
- Experience with OpenCV and classical CV techniques (geometry, camera calibration, image processing)
- Familiarity with model optimization and deployment (ONNX, TensorRT, quantization, or similar)
- Experience working with large image/video datasets and labeling workflows
- BS/MS in Computer Science, Electrical Engineering, or a related field, or equivalent experience
Nice to have
- C++ for performance-critical code
- Edge deployment experience (NVIDIA Jetson, mobile, embedded)
- 3D vision, multi-camera systems, SLAM, or sensor fusion (LiDAR, depth)
- Experience with vision-language or foundation models (CLIP, SAM, VLMs)
- MLOps tooling (Docker, Kubernetes, experiment tracking, CI/CD for ML)
- Publications or open-source contributions in CV/ML