Hivemapper is building the world's freshest map using street-level imagery contributed by a community of everyday drivers, large fleets, and everyone in between. We have over 60,000 contributors around the world, and have now mapped over 13M unique kilometers, or more than 21% of the world's roads.
Map data customers use Hivemapper’s developer-friendly APIs to access fresher road imagery and map feature datasets than any centralized mapping project can offer. Some examples of map data customers include enterprise technology, mapping, robotaxis, rideshares, and real estate!
Position Overview
Hivemapper data scientists work with engineering to confirm reasoning and validation about data and models in our production systems. We help engineering, product, and sales teams interpret data in the face of statistical uncertainty and data ambiguity. We also develop metrics and experimental designs that capture performance aspects of our mapping systems from collection to processing. Examples of areas the Hivemapper data science team is involved in include building representative and high quality datasets for the AI team, developing statistical models and visualizations to understand and build data quality metrics, and managing the quality as well as supply/demand of AI Trainers (data labelers) across the Hivemapper platform.
Key Responsibilities
- Expand and improve robust quality assurance data evaluation tools and reporting dashboard for map data.
- Manage inflow rate, quality verification and volume of collected data from the Hivemapper mapping network fleet of devices.
- Contribute to developing and implementing rigorous validation processes to ensure high-quality output from Map AI Trainers.
- Develop new metrics, interpret trends, and investigate anomalies in collected map data.
- Iterate with AI engineering partners on effectiveness of new datasets.
- Build visualization tools to review.
- Track and assess key performance indicators to gauge the success of data quality initiatives.
Qualifications
- Degree in a quantitative field (engineering, math, statistics, or economics)
- Demonstrated knowledge of Python/SQL/R data analysis libraries and packages
- Familiarity with Git, Grafana, Mode, & ElasticSearch
- Understanding of machine learning and mapping fundamentals
- Proven track record of performance and strong attention to detail and ability to manage multiple tasks in a fast-paced environment.
- Excellent communication and collaboration skills.
What we offer
- Medical, dental, and vision benefits plus FSA
- Family leave
- 401(k) program
- Unlimited Flex PTO
- Commuter benefits
- Paid lunch