Production ML Engineer — Real-Time Fraud

Latitude; Seattle (WA); Hybrid; USD 180,000 - 270,000; Full time

Benefits offered by this job

Equity

401(k) plan

Medical, dental, and vision benefits

Wellness stipends

Job summary

Stripe’s Radar ML team seeks to own ML problems from conception to production—analyzing fraud patterns, exploring large-scale data, selecting modeling approaches, deploying models, and improving them based on production performance.

You will work on transformer architectures for payment data and graph-powered insights, applying LLMs to evolving abuse, and prototyping protections with strategic users. Join Stripe to ship impactful ML at scale.

Qualifications

• 2+ years of experience developing, evaluating, and deploying ML models in a production environment.
• Strong foundations in ML, data analysis, statistics, model evaluation, and experiment design.
• Strong programming and software-engineering skills for production ML applications.
• Experience building or operating production ML systems, including data pipelines, distributed training, low-latency inference, deployment, or monitoring.
• 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.

Responsibilities

• Build, train, evaluate, and deploy models that detect fraud and abuse across Stripe’s global network.
• Investigate emerging fraud and abuse patterns, identify where ML can help, and rapidly develop effective solutions.
• Design features, datasets, evaluation methods, and experiments for noisy, delayed, and adversarial environments.
• Improve model architectures, training methods, and production systems to increase model quality, coverage, and adaptability.
• Monitor production behavior and improve models as data, customer needs, and attack patterns change.
• Balance model quality with legitimate-user impact, latency, reliability, and operational complexity.
• Partner with engineering, product, data science, risk experts, and leading Stripe users to turn modeling improvements into differentiated Radar products.
• Contribute to reusable tools and AI-assisted workflows that help the team develop and operate ML systems more effectively.

Skills

ML basics

Production ML

Programming

Distributed systems

Problem solving

Communication

Job description

Stripe’s Radar ML team seeks to own ML problems from conception to production—analyzing fraud patterns, exploring large-scale data, selecting modeling approaches, deploying models, and improving them based on production performance.

You will work on transformer architectures for payment data and graph-powered insights, applying LLMs to evolving abuse, and prototyping protections with strategic users. Join Stripe to ship impactful ML at scale.