Machine Learning Engineer, Transaction Risk

Stripe • Seattle, WA

21h

About The Position

The Machine Learning Engineer will build and own production machine learning systems for Stripe Radar, protecting businesses from fraud and abuse while allowing legitimate customers through. The role spans the full lifecycle of ML initiatives, from identifying high-impact problems and defining solutions to building, deploying, monitoring, and improving models and their supporting systems as data, users, and attackers change.

The work may include abuse protections across the customer lifecycle, customizable fraud systems for Stripe’s largest users, and risk intelligence for global payment methods. It may use transformer models over payment data, graph intelligence, and LLMs to detect emerging attacks. The engineer will lead major initiatives, contribute to new products and mission-critical systems at Stripe scale, and help set the team’s technical standards.

Requirements

• At least 5 years of experience developing, evaluating, and deploying machine learning models in production.
• Track record of leading ML projects from problem definition to production with measurable impact.
• Deep foundations in machine learning, statistics, model evaluation, and experiment design.
• Strong programming and software-engineering skills, including writing tested, maintainable code for production ML applications.
• Experience designing and operating production ML systems, including several of: large-scale data and feature pipelines, distributed model training, low-latency inference, model deployment, or production monitoring.
• Experience mentoring engineers or technically leading projects with multiple contributors.
• Ability to investigate ambiguous problems, reason from data, and choose pragmatic technical approaches.
• Ability to communicate technical ideas and results clearly and collaborate across disciplines.

Nice To Haves

• Experience applying ML to fraud detection, integrity, trust and safety, identity, cybersecurity, or another adversarial domain.
• Experience developing or productionizing modern deep learning, graph-learning, or LLM-based approaches.
• Experience building and optimizing real-time, low-latency ML systems at scale.
• Experience owning the operational health of critical ML systems, including on-call, incident response, and migrations.
• Experience rapidly building 0→1 products or working directly with customers.
• Experience building AI-assisted tooling or agents that measurably increased a team’s velocity.

Responsibilities

• Lead ML projects end to end, from problem framing and opportunity sizing through deployment, monitoring, and iteration.
• Build, train, evaluate, and deploy models that detect fraud and abuse across Stripe’s global network, and own the production systems that run them.
• Investigate emerging fraud and abuse patterns, identify where ML can have the greatest impact, and turn insights into shipped protections.
• Design features, datasets, and evaluation strategies for noisy, delayed, and adversarial environments, maintaining rigorous experimentation.
• Make architecture and modeling tradeoffs among model quality, legitimate-user impact, latency, reliability, and operational cost.
• Lead incident response for model regressions, reduce operational toil, and make owned systems easier for others to build on.
• Partner with engineering, product, data science, risk experts, and Stripe users to turn modeling improvements into Radar products.
• Create reusable components, tools, and AI-assisted workflows to improve team efficiency.
• Mentor engineers, provide design and code reviews, and help new teammates ramp up.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed