Strava Jobs (NOW HIRING)

We are looking for a Machine Learning Engineer to join the growing AI and Machine Learning team at Strava. This team is responsible for sophisticated machine learning models and systems which provide value to Strava athletes including personalization, recommendations, search, and trust and safety. The team also maintains the ML platform and infrastructure that enables our team to iterate on models quickly and deploy them reliably at scale.

This is an important role in the ML team and across Product teams designing, roadmapping, and implementing innovative machine learning algorithms. We value full stack ML engineers who are able to work on all parts of an ML pipeline from model building, evaluation, optimizing performance, and ensuring the scalability and reliability of these production models. We also seek those who can improve the systems and tools behind the ML pipeline to further empower the team.

We follow a flexible hybrid model that translates to more than half your time on-site in our San Francisco Office — three days per week.

• Build for a Well Loved Consumer Product: Work at the intersection of AI and fitness to launch and optimize product experiences that will be used by tens of millions of active people worldwide

• Craft End to End AI Systems: Contribute to projects powered by ML on the Strava platform end-to-end, from initial model prototyping to shipping production code to scaling and optimizing inference and deployment

• Shape AI at Strava: Bring your voice and creativity to a highly collaborative team with a range of experience levels. Work across teams to deploy ML solutions in multiple surfaces and build out our technical ML capabilities.

• Innovate in AI for Fitness: Design and develop novel models and methodologies to take on novel problems that improve athlete experience, including recommendation systems, activity prediction, and personalized insights.

• Build from a rich dataset: Explore and use Strava's extensive unique fitness and geo datasets from millions of users to extract actionable insights, inform product decisions, and optimize existing features

• Driving innovation with Product in mind: Stay up-to-date with the latest research in machine learning, AI, and related fields. Experiment, advocate and get buy-in for innovative techniques to improve existing products or explore new features that result in step function changes to how we build AI at Strava.

• Be Accountable: Owning your work end-to-end and being accountable for the outcomes in the projects you contribute to. Ensure the end-to-end system delivers as expected through collaboration with partners.

• Analyzing the Data: Work closely with product managers, data scientists, and engineers to find opportunities for applying machine learning to drive business impact and enhance Strava's features and measure impact.

• Collaborating in and across teams: Build relationships and communicate with cross-functional partners and product verticals to identify opportunities and bring the team's technical vision to life.

• Raising the ML standard: Use best practices for model development, deployment, and maintenance. Keep a high bar for quality in everything you do.

• Being passionate about the work you are doing and contributing positively to Strava's inclusive and collaborative team culture and values

• Have worked on impactful machine learning problems delivering incremental progress towards long-term goals.

• Have demonstrated solid interpersonal and communication skills, and collaborate across teams.

• Have experience building, shipping, and supporting ML models in production at scale.

• Have experience with exploratory data analysis and model prototyping, using languages such as Python or R and tools like Scikit learn, Pandas, Numpy, Pytorch, Tensorflow, and Sagemaker.

• Have built and worked on data pipelines using large scale data technologies (like Spark, Hadoop, EMR, SQL, and Snowflake).

• Are experienced and interested in production ML model operational excellence and best practices, like automated model retraining, performance monitoring, feature logging, and A/B testing.

• Have built backend production services on cloud environments like AWS, using languages like (but not limited to) Python, Ruby, Java, Scala, and Go.