About the job
Blue River Technology creates intelligent machinery for agriculture, construction, and forestry, aiming to make these industries safer and more sustainable. The team emphasizes practical, detail-oriented solutions that address real operational challenges. Projects are managed with care, focusing on measurable progress and improved profitability while reducing dependence on limited labor resources.
Headquartered in Santa Clara, California, Blue River Technology applies advanced technology to significant industry problems.
Role overview
The Senior Data Scientist manages and curates complex datasets, with a focus on images and sensor data, to support the trust and safety of autonomous systems. Collaboration with data engineers and field technicians is central, ensuring data quality and supporting teams working in computer vision and robotics.
Main responsibilities
- Curate, define, and manage datasets (images and sensor data) to improve the safety and reliability of autonomous systems.
- Collaborate with data engineers and field data technicians to analyze fleet data and identify key needs.
- Build frameworks for cataloging and accessing scenario-based data for teams in computer vision and robotics.
- Oversee data ingestion, troubleshoot issues, and maintain high data quality for training and testing computer vision algorithms.
- Address both immediate and long-term data quality challenges.
- Support internal teams with data and infrastructure resources as needed.
- Advise on improving the stability, security, efficiency, and scalability of image data pipelines.
- Promote strong code quality through unit testing, automation, and code reviews.
- Analyze the link between customer experience and virtual performance in key scenarios, ensuring test cases for safety and productivity are well covered.
Requirements
- Master’s degree in Mathematics, Physics, Data Science, or a related field, plus 5 years of relevant experience.
- At least 5 years of hands-on experience building and deploying computer vision and machine learning data pipelines, including semantic segmentation, image and video classification, and both supervised and unsupervised learning.
- Minimum 4 years collaborating with data engineers, data scientists, software engineers, and field staff throughout the machine learning system lifecycle.
- Proficiency in non-parametric statistical tests and analysis on large image-based datasets using libraries such as sklearn, scikit-image, and scipy.
This position is based in Santa Clara, CA.
