Computer Vision Engineer

About Workerbee

Workerbee connects workers with employers through trusted introductions. By joining Workerbee you can be matched for project-based, contract, or permanent opportunities with leading organizations. Over time, Workerbee helps you:

• Keep a living record of what you have actually accomplished
• See how your experience carries across roles and paths
• Explore options without pressure to apply
• Move through change with clarity instead of urgency

We are connected to those who hire talent and are in need of Computer Vision Engineers. In this work, you will help employers solve complex problems and bring real value through hands-on expertise in computer vision model development and deployment.

Responsibilities

• Build detection, segmentation, classification, and OCR models against real customer image and video data
• Own the data pipeline end to end, including collection, annotation standards, augmentation, class balance, and label quality review
• Train, evaluate, and fine-tune models in PyTorch while tracking precision, recall, and failure modes on holdout and edge cases
• Optimize models for their deployment target using quantization, pruning, and runtimes such as TensorRT, ONNX Runtime, or Core ML
• Move working prototypes into production with drift monitoring, retraining triggers, and repeatable evaluation

Requirements

• 5+ years applying computer vision in production environments with Python and PyTorch or TensorFlow
• Depth in modern architectures including CNNs, vision transformers, YOLO family detectors, and segmentation or multimodal models
• Experience with OpenCV and annotation tooling, and the resourcefulness to build datasets when clean labeled data does not exist
• Familiarity with edge and embedded deployment constraints, including latency, memory, and power budgets
• Ability to turn a loosely defined business problem into a measurable vision task with an honest accuracy target

Benefits

• Earlier visibility into opportunities
• Better-fit introductions
• Access to meaningful work
• Less application noise
• A network that improves over time