Strong experience in computer-vision algorithms—primarily YOLO-based models—for object detection tasks.
The role involves fine-tuning and retraining off-the-shelf models, as well as applying techniques like quantization and distillation to optimize models for edge deployment.
Candidates should be proficient in Docker for containerizing FastAPI-based web services and publishing results to message brokers.
Familiarity with Kubernetes and Google Cloud Platform is essential for operating within our production architecture.
Experience in Python, Typescript, and scalable architectures is preferred.
Top Skills Needed:
Experience with YOLO-based models and ML frameworks