Machine Learning Engineer, Radar

Who we are

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 Radar ML team builds the machine learning systems behind Stripe’s Radar fraud and abuse products. Our models protect a significant share of internet commerce, make real-time decisions at Stripe scale, and have a direct, measurable impact on Stripe and its users.

Fraud and abuse are adversarial and constantly evolving. This makes Radar a uniquely demanding ML environment: we pursue ambitious ML projects and rapidly adapt to an evolving risk landscape, while operating systems that must meet high standards for model quality, latency, and reliability.

Now the team is expanding in three directions: moving beyond payments to protect leading AI companies across the full customer life-cycle, giving enterprises more customizable and adaptable fraud protection, and extending Stripe’s risk intelligence across global payment methods.

What you’ll do

• You will own ML problems from conception to production: analyzing new fraud and abuse patterns, exploring large-scale datasets, selecting modeling approaches, designing evaluations, deploying models, and improving them based on production performance.

• Your work may include developing transformer architectures for payment data, building graph-powered intelligence across consumers and payment methods, applying LLMs to emerging forms of abuse, or rapidly prototyping simple new protections with strategic users. You will have opportunities to ship 0→1 products, and to improve mission-critical ML models operating at Stripe scale.

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.

• Who you are

• You are a fast, pragmatic problem solver with deep ML expertise and a bias toward action. You are excited to work at the frontier of payments and AI - turning advances in machine learning into production systems that address new forms of fraud and abuse.

• 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

• 2+ years of experience developing, evaluating, and deploying machine learning models in a production environment.

• Strong foundations in machine learning, data analysis, statistics, model evaluation, and experiment design.

• Strong programming and software-engineering skills, with experience writing tested, maintainable code for production ML applications.

• Experience building or operating production ML systems, including one or more of large-scale data and feature pipelines, distributed model training, low-latency inference, model deployment, or production monitoring.

• Ability to investigate ambiguous problems, reason from data, and choose pragmatic technical approaches.

• Ability to communicate technical ideas and results clearly and collaborate effectively across disciplines.

• Preferred qualifications

• Experience owning an ML problem across the full lifecycle, from problem framing and data exploration through deployment, monitoring, and iteration.

• 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 applying ML to fraud detection, integrity, trust and safety, identity, cybersecurity, or another adversarial domain.

• Experience rapidly building 0→1 products, working directly with customers, or operating effectively in a fast-moving environment.

• Active interest in the latest ML developments, and how they can be leveraged to solve business problems.