192K–318K USD / year
Machine Learning Engineer, Transaction Risk
Machine learningHybrid — New York, Seattle, United States
Published on 2026-11-10
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
Own production machine-learning systems that help Stripe Radar detect fraud and abuse while minimizing friction for legitimate customers. Work spans emerging threats, customer-lifecycle protections, and risk intelligence across global payment methods, using approaches such as transformers, graph learning, and LLMs.
About the company
Stripe provides payment infrastructure and financial tools that help businesses accept payments, manage subscriptions, and move money globally. It serves startups through large enterprises with APIs for online and in-person commerce.
The team
Transaction Risk team, within Data & Data Science.
Stack
Machine learningTransformersGraph learningLLMs
What you'll do
- Lead ML initiatives from problem framing through deployment, monitoring, and iteration.
- Build, evaluate, deploy, and operate fraud- and abuse-detection models.
- Investigate new attack patterns and ship effective protections.
- Design features, datasets, and rigorous evaluation strategies for adversarial data.
- Balance model performance with user impact, latency, reliability, and cost.
- Own incident response and operational health for production ML systems.
- Partner with engineering, product, data science, risk experts, and customers.
- Mentor engineers and develop reusable tools and AI-assisted workflows.
What we're looking for
- 5+ years developing, evaluating, and deploying production ML models.
- Led ML projects from problem definition to production with measurable impact.
- Strong foundations in machine learning, statistics, evaluation, and experiment design.
- Strong programming and software-engineering skills; writes tested, maintainable production code.
- Experience designing and operating production ML systems, such as data pipelines, distributed training, low-latency inference, deployment, or monitoring.
- Experience mentoring engineers or technically leading multi-contributor projects.
- Can investigate ambiguous problems, reason from data, and communicate clearly across disciplines.
Nice to have
- Experience in fraud, trust and safety, identity, cybersecurity, or another adversarial domain.
- Experience with deep learning, graph learning, or LLMs in production.
- Experience building real-time, low-latency ML systems at scale.
- Experience with on-call, incident response, and migrations for critical ML systems.
- Experience launching 0-to-1 products or working directly with customers.
- Experience building AI-assisted tools or agents that improve team velocity.
Benefits
- Equity
- Company bonus
- 401(k) plan
- Medical, dental, and vision benefits
- Wellness stipends