Computer Vision Engineer

Computer Vision Engineer

Quantaleap is looking for a hands-on Computer Vision Engineer who can design, train and deploy deep-learning models that power real-time image and video analytics. You will collaborate with product, data and backend teams, so clear, proactive communication is essential.

Key responsibilities

• Research and prototype computer-vision algorithms for anomaly detection, object detection, tracking and segmentation.

• Create end-to-end image-processing and computer-vision pipelines.

• Train, fine-tune and optimise CNN and Transformer models in PyTorch or TensorFlow.

• Package and deploy models to cloud or edge environments with Docker and Kubernetes.

• Automate pipelines for image and video collection, augmentation and annotation.

• Monitor model performance in production and drive continuous improvement.

• Document findings and present results to technical and non-technical stakeholders.

Must-have skills

• 3–5 years building computer-vision solutions in production.

• Strong knowledge of computer vision and deep learning, including CNNs and Vision Transformers such as YOLO.

• Proficiency with PyTorch or TensorFlow, OpenCV and Python.

• Experience deploying models through REST or gRPC APIs, or on-device.

• Excellent written and verbal communication.

Nice to have

• Knowledge of CUDA, TensorRT or other inference-time optimisers.

• Experience with AWS or GCP ML services and streaming data such as Kafka or Kinesis.

• Experience implementing agentic AI.

• Familiarity with MLOps practices including CI/CD and model versioning.