What you'll doIn this role, you will own ML work across the full lifecycle: researching new fraud patterns, building and deploying models, and sharing results directly with top Stripe customers. You will have opportunities to optimize Stripe's most intensive ML models, and opportunities to ship 0-to-1 products from scratch.
Responsibilities- Build, train, evaluate, and deploy ML models that detect fraud across Stripe's global payments network
- Research emerging fraud patterns like token theft and develop ML solutions to address them
- Apply advances in deep learning to improve model quality and detection rates at scale
- Co-build new fraud and abuse products directly with top users
Who you areWe're looking for someone who meets the minimum requirements to be considered for the role. If you meet these requirements, you are encouraged to apply. The preferred qualifications are a bonus, not a requirement.
Minimum requirements- 6+ years of industry experience training, evaluating, and deploying ML models in a production environment
- Proficiency in Python and common data and ML frameworks like SQL, Spark, and PyTorch
- Strong knowledge of production ML systems; and data analysis, statistics, and experiment design fundamentals
- Active interest in the latest ML developments, and how they can be leveraged to solve business problems
Preferred qualifications- Experience building and optimizing real-time, low-latency ML infrastructure at scale
- Strong software engineering skills and ability to design ML solutions through entire product stack
- Experience applying ML to fraud detection, risk modeling, or a closely related domain
- Experience designing ML products used by millions of users
