Mapbox is the leading real-time location platform for a new generation of location-aware businesses. Mapbox is the only platform that equips organizations with the full set of tools to power the navigation of people, packages, & vehicles everywhere. More than 3.9 million registered developers have chosen Mapbox because of the platforms flexibility, security, & privacy compliance. Organizations use Mapbox applications, data, SDKs, & APIs to create customized & immersive experiences that delight their customers.

What We Do

The Telemetry team collects location telemetry from mobile Mapbox SDKs & uses it to improve our map, directions, & travel times, as well as to provide insights into human mobility patterns. To do so, we build & deploy pipelines to process, anonymize, & analyze billions of location probes per day. The customers of our unique, privacy-centric datasets on traffic patterns and human activity range from major corporations to local governments & NGO; but we are also committed to making data accessible to smaller developers, & work on a number of community-driven & open-source projects. We're a diverse team of backend engineers, data engineers, & data scientists located around the world, but we work closely together, support each other's growth & learning, & share an enthusiasm for deriving interesting & useful insights out of geospatial data.

To see some examples of our work, check out some of our blog posts from the past year:

• Tracking how COVID changed mobility patterns throughout the world
• Shopping & sunbathing: how America responds to quarantine
• Tracking retail recovery using Movement data
• Using Movement data to analyze airport traffic
• How location data becomes traffic data

What Youll Do

As a ML engineer, You will be responsible for architecting, building, & maintaining production systems for Mapboxs Traffic or Movement products & ML Engine. Your technical contributions will include:

• Designing & building new ML & data pipelines, as well as optimizing existing ML & data pipelines in Python & Spark/PySpark.  
• Building tools for automated quality assurance & data exploration.
• Designing & building APIs for delivering data to customers.
• Leveraging geospatial algorithms to optimize pipelines, as well as creating automated tuning & outlier detection algorithms.
• Partnering with data scientists to make improvements to our models for determining patterns in movement and/or traffic.
• Participate in an on-call rotation to ensure our systems remain available to customers 24/7. Team members alternate as the on-call primary responder, which may require immediate response outside normal working hours, including weekends.

Outside of your direct technical contributions you will:

• Collaborate with other teams within Mapbox to expand use of location telemetry data throughout the company.
• Mentor colleagues, especially with respect to Spark optimization & best practices.
• Participate in code & design reviews

There are also ample opportunities to act as an evangelist in the larger community by writing blog posts, engaging with our community partners & journalists to help them make the best use of our data, & collaborating with our academic partners on white papers.

What We Believe are Important Traits for This Role

• Ability to write approachable, performant code with comprehensive tests & thorough documentation.
• Excellent communication skills, both written & verbal.
• Experience building & maintaining data pipelines with large datasets
• Experience designing & building systems at scale using AWS infrastructure
• A highly autonomous & self-driven approach
• A solid engineering foundation with an interest in geospatial data & big data analysis
• Comfort being vulnerable when you dont know the answer, & knowing how to ask for help.
• Ability to communicate how complex systems work to both engineers as well as customers or business stakeholders
• Experience & enthusiasm for mentoring teammates, providing technical feedback, & sharing knowledge with others

You may need strong skills in the following areas, which form the foundation of our technical stack. We dont expect anyone to be an expert in all areas. However, familiarity with more than two is a bonus, & you should be ready to learn any of them. In the bigger picture, curiosity about spatial data & our planet is highly encouraged, as is mentoring aptitude or experience.

• Python
• Experience with distributed processing pipelines (Hadoop, Spark, Airflow, Dask)
• AWS infrastructure (e.g., S3, EMR, ECS, Athena, Lambda, DynamoDB, IAM)
• Building secure & stable APIs
• Experience working with very large datasets statistical analysis, data quality control, optimizing storage

What We Value

In addition to our core values, which are not unique to this position & are necessary for Mapbox leaders:

• We value high-performing creative individuals who dig into problems & opportunities.
• We believe in individuals being their whole selves at work. We commit to this through supportive health care, parental leave, flexibility for the things that come up in life, & innovating on how we think about supporting our people.
• We emphasize an environment of teaching & learning to equip employees with the tools needed to be successful in their function & the company.
• We strongly believe in the value of growing a diverse team & encourage people of all backgrounds, genders, ethnicities, abilities, & sexual orientations to apply.

By applying for this position, you acknowledge that you agree to the Mapbox Privacy Policy which is linked here.

Mapbox is an EEO Employer - Minority/Female/Veteran/Disabled/Sexual Orientation/Gender Identity

#LI-Remote