Top Computer Vision Jobs in Denver & Boulder, CO

The Machine Learning Engineer will develop editable visuals combining computer vision and machine learning, enabling chat-driven figure editing and leveraging biological understanding to produce accurate visuals.

Lead and execute the production photogrammetry pipeline: design, build, train, and deploy 3D reconstruction systems at scale. Drive technical direction, optimize for speed and robustness, own observability and CI/CD, mentor engineers, integrate foundation 3D models and agentic AI tooling, and translate strategic goals into shipped work.

Lead a small team to research, develop, train, optimize, and deploy computer vision and multimodal fusion AI/ML models for remote sensing (EO/SAR). Analyze large datasets, translate research into operational systems, present technical findings to customers, and produce supporting documentation and user guides.

Build end-to-end front-end tooling and active-learning agents for a spatial CV platform. Train and deploy lightweight CV models, create pre-labeling and annotation systems, design planogram and spatial interfaces, and iterate rapidly to deliver intuitive visual workflows for researchers and non-technical users.

Design real-world computer vision tasks, build reference solutions and evaluation components in Python, assess AI model outputs, identify failure modes, and develop structured rubrics and guidelines. Collaborate with experts to maintain high-quality training data and evaluation standards for multimodal and generative vision systems. Part-time, remote contractor role (~20 hours/week).

The Computer Vision Engineer will develop and improve sports video models, conduct experiments, and collaborate with data teams to productionize models, focusing on player detection and tracking.

Design, improve, and deploy production-grade computer vision systems for sports video: detection, multi-object tracking, camera calibration, homography, field registration, identity association, and robustness across varied cameras and video quality. Lead experiments, adapt models to new domains, collaborate with data and engineering teams, and drive end-to-end solutions from prototype to production.

Lead design and productionization of egocentric and warehouse perception systems: data capture, camera rigs, calibration, multi-view 3D and pose estimation, automated labeling pipelines, model training/optimization, deployment, and establishing dataset quality standards for embodied AI.

Review trainer-submitted image-question pairs and verify golden answers for accuracy and consistency. Flag and document incorrect, ambiguous, or incomplete responses, provide corrective feedback, track recurring errors, and escalate unclear cases. Ensure trainer output meets project quality standards.