Computer Vision Engineer

Job description

We're looking for a Computer Vision Engineer to build visual intelligence features for a product that runs across connected devices and mobile apps.

This is a hands-on engineering role, not a research one: you'll take CV models from training to production, with a strong focus on making them run fast on resource-constrained devices.

What you'll do:

- Design, train, and deploy CV models - object detection, classification, segmentation, visual analysis;

- Optimize models for edge and mobile inference (quantization, pruning, distillation);

- Build data pipelines for image and video processing, including annotation and dataset versioning;

- Set up monitoring and retraining workflows for models in production;

- Work with backend and mobile teams to integrate model outputs into user-facing features.

Requirements:

- 3+ years in applied computer vision or ML with a strong CV focus;

- Solid deep learning background: CNNs, detection and segmentation architectures (YOLO, Faster R-CNN, U-Net), vision transformers;

- Python, PyTorch or TensorFlow, OpenCV;

- Experience deploying and maintaining CV models in production;

- Hands-on with on-device inference: ONNX, TensorRT, TensorFlow Lite, Core ML, or OpenVINO;

- Cloud platforms (GCP, AWS, or Azure) and container-based deployments;

- English: Intermediate or higher.

Nice to have:

- MLOps tools (MLflow, Airflow, Vertex AI);

- Real-time video processing at scale (FFmpeg, GStreamer, Kafka);

- Edge AI or mobile ML experience.