Machine Learning Engineer II, Search Data

What We Do

The Search Data team supplies address, place, and points of interest (POI) data for global searches in countries around the world. Search is crucial for our customers’ applications and we are a key partner to the Maps and Navigation organizations at Mapbox. Whether you’re trying to find a place among the vast ocean of data on a global map or to find the exact location of a venue a few miles down the road, Search is in the critical path of our customers’ experiences.

What You'll Do

We are looking for a Senior Machine Learning Engineer to help us build new datasets and pipelines for in-vehicle navigation applications. As a Machine Learning Engineer, you will have the opportunity to work on the Search Data team at Mapbox - an exciting and challenging opportunity!

We process batch data from thousands of sources and use ETL data pipelines to prepare it for our search engines. This area of our work presents a range of challenging algorithmic, scaling, and quality assessment opportunities. You will work with diverse datasets at scale (up to 1TB) - hundreds of millions of records - and play a vital role in ensuring the high quality of our products. If you are passionate about machine learning engineering and ready to take on new challenges, we invite you to join our team!

As a Machine Learning Engineer on the Search Data team, you will:

• Work with specialized geospatial data sets including, addresses, road networks, buildings, POIs.
• Form data driven hypotheses
• Develop ML models and run experiments to test your hypotheses
• Operationalize successful experiments
• Monitor and maintain operational ML models
• Implement automated quality metrics to ensure we are continuously delivering high quality data to our customers
• Mentor other software engineers to develop all aspects of their engineering skills sets, including participating in design and code reviews

What We Believe are Important Traits for This Role

• 5+ years of industry experience working with machine learning models in production
• A scientific mindset. You are able to collect data, formulate hypotheses, and create experiments which test those hypotheses.
• Excellent documentation skills to keep records of your analyses, hypotheses, experiments, and operational metrics.
• Experience with AWS technologies including Glue and EMR
• Proficiency in SQL
• Proficiency in at least one modern programming language (Python, Scala, or Java) suitable for machine learning and data processing
• Familiarity with PySpark
• Integrating data with APIs and querying data through APIs

Nice to Have Traits for This role

• Experience with geospatial data analysis and processing
• Experience with data pipelines
• Experience with Natural Language Processing (NLP)

What We Value

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

• We value high-performing creative individuals who dig into problems and 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, and innovating on how we think about supporting our people.
• We emphasize an environment of teaching and learning to equip employees with the tools needed to be successful in their function and the company.
• We strongly believe in the value of growing a diverse team and encourage people of all backgrounds, genders, ethnicities, abilities, and sexual orientations to apply.

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

Mapbox participates in E-Verify to confirm employee work authorization. Please refer to the Notice of E-Verify Participation and Right to Work posters for more information.

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

#LI-Remote