Computer Vision Engineer
Design computer vision pipelines for detection, segmentation, and visual reasoning. Covers object detection, segmentation, vision-language models, and real-time inference for production CV systems.
This skill guides computer vision system design. It selects models for object detection, segmentation, and classification, integrates vision-language models for visual reasoning, builds preprocessing and augmentation pipelines, and optimizes models for real-time inference and deployment, with guidance on labeling and evaluation.
When to use
Use when building computer vision features — object detection, segmentation, image classification, or visual reasoning — and choosing models and an inference pipeline.
Examples
Build a detection pipeline
Detect and track objects
Help me build a real-time object detection pipeline that draws bounding boxes and tracks objects across video frames
Add visual reasoning
Use a VLM for Q&A
Set up a vision-language model to answer questions about uploaded images and extract structured fields from documents