TL;DR
Machine Learning Engineer at Stripe building fraud detection and payment decisioning models. Owns end-to-end ML lifecycle for products like Radar and Adaptive Acceptance, working with large-scale payment datasets and real-time inference systems.
About Stripe
Stripe is a financial infrastructure platform for businesses. Millions of companies - from the world’s largest enterprises to the most ambitious startups - use Stripe to accept payments, grow their revenue, and accelerate new business opportunities. Our mission is to increase the GDP of the internet, and we have a staggering amount of work ahead. That means you have an unprecedented opportunity to put the global economy within everyone's reach while doing the most important work of your career.
About the team
The Payment Intelligence ML Engineering (PIME) optimizes each of the billions of dollars of transactions processed by Stripe annually on behalf of our customers, maximizing successful transactions while minimizing payment costs and fraud. We leverage ML to serve real-time predictions as part of Stripe’s payment infrastructure and risk controls. We own products like Radar, Adaptive Acceptance, and Identity end-to-end, operating lightning fast world-scale services and cutting-edge ML models.
What you’ll do
We are looking for Machine Learning Engineers to own the end-to-end lifecycle of applied ML model development and deployment in service of consumer facing products like Radar, Adaptive Acceptance, and Identity. You will work closely with software engineers, machine learning engineers (MLE), data scientists (DS), and ML platform infrastructure teams to design, build, deploy, and operate Stripe’s ML-powered payment decisioning systems, including improving existing ML models and developing new ML solutions.
Responsibilities
- Design and deploy new models using tools (such as Spark, Presto, XGBoost, Tensorflow, PyTorch) and iteratively improve verification and fraud models to protect millions of users from fraud
- Envision and develop new models for fraud detection i.e work with large payment datasets to find creative new methods of detecting and deterring fraudulent behavior.
- Propose new feature ideas and design real-time data pipelines to incorporate them into our models.
- Integrate new signals into ML pipelines, derive new ML features, and build workflows to make this process fast
- Integrate new models and behaviors into Stripe’s core payment flow
- Collaborate and execute projects cross-functionally with the data science, product management, infrastructure, and risk teams
- Ensure engineering outcomes meet or exceed established standards of excellence in code quality, system design, and scalability
- Mentor engineers earlier in their technical careers to help them grow
- Propose and implement innovative product ideas to reduce costs and combat fraud at Stripe
Who you are
We'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
- Over 3+ years industry experience building machine learning applications in large scale distributed systems.
- 2+ year of experience working within a team responsible for developing, managing, and optimizing ML models or ML infrastructure
- Experience designing and training machine learning models to solve critical business problems
- Experience performing analysis, including querying data, defining metrics, or slicing and dicing data to model performance and business metrics
Preferred qualifications
- An advanced degree in a quantitative field (e.g. stats, physics, computer science)
- Proven track record of building and deploying machine learning systems that have effectively solved critical business problems
- Experience in adversarial domains like Payments, Fraud, Trust, or Safety
- Experience working in Python, Java and / or Ruby codebases
- Experience in software engineering in a production environment.