Remote ML Engineer — Fraud & Risk (Radar)

Latitude; San Francisco (CA); Hybrid; USD 180,000 - 270,000; Full time

Job summary

Stripe’s Radar ML team is expanding, shaping fraud and abuse defenses with advanced ML at scale. You will own ML problems from conception to production, exploring datasets, selecting models, evaluating performance, deploying and iterating based on production results.

We seek practical, fast-moving experts with strong ML foundations, who can ship 0→1 protections and collaborate across product, data science, and risk functions. Hybrid or remote work options are available in the US.

Qualifications

• 2+ years of experience developing, evaluating, and deploying ML models in production.
• Strong foundations in ML, data analysis, statistics, evaluation, and experiment design.
• Strong programming and software-engineering skills for production ML apps.
• Experience building/operating production ML systems including data pipelines, distributed training, low-latency inference or monitoring.
• Ability to investigate ambiguous problems, reason from data, and choose pragmatic approaches.
• Ability to communicate technical ideas clearly and collaborate across teams.

Responsibilities

• Build, train, evaluate, and deploy models that detect fraud and abuse across Stripe’s global network.
• Investigate emerging fraud patterns and rapidly develop effective ML solutions.
• Design features, datasets, evaluation methods, and experiments for noisy/adversarial environments.
• Improve model architectures, training methods, and production systems for quality and adaptability.
• Monitor production behavior and adapt models as data and threats evolve.
• Balance model quality with latency and reliability under real-world constraints.
• Collaborate with engineering, product, data science, and risk teams to apply modeling improvements.
• Contribute to reusable tools and AI-assisted workflows for the team.

Skills

ML in production

Python

Data analysis

Experiment design

Effective communication

Tools

Distributed systems

Low-latency inference

Graph learning

LLMs

Job description

Stripe’s Radar ML team is expanding, shaping fraud and abuse defenses with advanced ML at scale. You will own ML problems from conception to production, exploring datasets, selecting models, evaluating performance, deploying and iterating based on production results.

We seek practical, fast-moving experts with strong ML foundations, who can ship 0→1 protections and collaborate across product, data science, and risk functions. Hybrid or remote work options are available in the US.