Who you are:

We are always looking for amazing talent who can contribute to our growth and deliver results! Geotab is seeking a Data Scientist Intern to join Geotab's maintenance analytics team, the team that turns raw vehicle telematics into predictive maintenance products used by fleets around the world. This isn't a shadow the team internship: our last intern in this role ended up designing and shipping an actual product feature. Comfortable with ambiguity, eager to own something end to end, and fluent enough with modern AI tooling to spend their time on the hard problems instead of the boilerplate. If you love technology, and are keen to join an industry leader - we would love to hear from you!

What you'll do:

As a Data Scientist Intern, you'll work directly with our data scientists on the full lifecycle of a predictive maintenance data product: exploring raw diagnostic and telemetry signals, prototyping features and models, and helping productionize the result into a data pipeline that ships real signals to customers. You'll use AI assisted workflows as a default part of how you work, not as a novelty, but because that's how the team operates day to day. The goal is for you to spend your term building something you can point to, not maintaining a dashboard. Before any of those ships, you'll validate the approach itself, exploring prior art and running quick experiments to confirm a signal or method is worth building on.

The opportunity:

• 4-8 month work-term beginning January 2027.
• Full-time, paid internship: Monday - Friday, 37.5hrs/week.
• Your first week at Geotab begins with 'GEO Launch' - a one-week Employee Orientation. Click here to learn more!
• Learn more about the Geotab Campus Program here.
• This posting is for an existing vacancy.

How you'll make an impact:

• Own a discrete analytics or pipeline project end to end, from problem framing and signal exploration through a working, demoable output, rather than a series of isolated, one off asks
• Explore raw diagnostic and telemetry signals in Google BigQuery; turn patterns into features, prototypes, and predictive models
• Contribute production quality Python/SQL to shared data pipelines, following the team's Git and code review practices
• Use AI coding/agentic tools deliberately to accelerate exploration, scaffolding, and debugging, so more time goes toward the actual problem
• Test and validate model outputs and pipeline reliability before deployment and metrics monitoring thereafter
• Present progress at sprint reviews and team technical sessions, and collaborate with data scientists, product, and other technical stakeholders
• Run exploratory analysis and a quick literature or prior-art scan on existing predictive maintenance approaches before committing to a modeling path
• Benchmark candidate approaches (features, model families, thresholds) against a baseline and document the tradeoffs

What you'll bring to the role: