2 months ago
San Bruno, CA, USAIntern
Responsibilities
- Build and improve computer vision models for detection, segmentation, and classification of materials and food.
- Curate, explore, and quality-assure large image and video datasets, identifying failure modes, duplicates, and labeling issues.
- Develop scalable training pipelines and experiment-tracking/reporting tools to make experiments reproducible and comparable.
- Design and run model evaluations and contribute to measurement of progress.
- Collaborate with engineering and data teams to move promising results toward production.
- Document methods and share findings with the team.
Requirements
- Currently pursuing or recently completed a degree in computer vision, machine learning, robotics, or a related field.
- Strong programming skills in Python and hands-on experience with a deep-learning framework.
- Solid grounding in modern computer vision, including object detection, segmentation, and representation learning.
- Experience training and evaluating models on real datasets and working with messy real-world data.
- Interest in translating research skills into practical, shipped systems.
- Preferred: experience with ClearML, Weights & Biases, MLflow, FiftyOne/Voxel51, CVAT, Roboflow, data or training pipelines, AWS, GCP, Docker, Kubernetes, publications, or open-source contributions in computer vision or machine learning.
Benefits
- Hybrid work in San Bruno, California.
- Flexible 3–6 month duration around the academic schedule.
- Immediate start date.
- Potential benefits and equity grant in addition to base compensation.