Machine Learning Engineer, Radar

Stripe; United States; Hybrid; USD 212,000 - 318,000; Full time

Benefits offered by this job

Equity

Performance bonus

401(k)

Medical, dental, and vision benefits

Job summary

Stripe's Radar ML team is hiring a senior ML engineer to own fraud-detection models across the full lifecycle, from research to deployment. You will optimize real-time models and collaborate with customers to ship new ML products from scratch.

You'll apply deep learning advances, work on token theft defenses, and help scale models across Stripe's global payments network, impacting billions of transactions and reducing fraud at scale.

Qualifications

• 6+ years of industry experience training, evaluating, and deploying ML models in a production environment.
• Proficiency in Python, SQL, Spark, and PyTorch.
• Strong knowledge of production ML systems and data analysis, statistics, and experiment design fundamentals.

Responsibilities

• Build, train, evaluate, and deploy ML models that detect fraud across Stripe’s global payments network.
• Research emerging fraud patterns like token theft and develop ML solutions to address them.
• Apply advances in deep learning to improve model quality and detection rates at scale.
• Co-build new fraud and abuse products directly with top users.

Skills

Python

SQL

Spark

PyTorch

Fraud detection

Experiment design

Tools

Spark MLlib

Docker

Job description

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 fraud detection models that protect Stripe's $1.9 trillion payment network from fraud. The team owns 10+ real-time deep learning models that must constantly evolve to stay ahead of fraudsters. Each ML improvement translates directly into dollar impact for Stripe and its users. The team's models also power the Radar product suite that tens of thousands of businesses use to screen payments and manage fraud. Radar is growing fast, and the team is actively building new products like defenses against AI token theft, free trial abuse, and programmatic attacks.

What you’ll do

In this role, you will own ML work across the full lifecycle: researching new fraud patterns, building and deploying models, and sharing results directly with top Stripe customers. You will have opportunities to optimize Stripe’s most intensive ML models, and opportunities to ship 0-to-1 products from scratch.

Responsibilities

• Build, train, evaluate, and deploy ML models that detect fraud across Stripe’s global payments network
• Research emerging fraud patterns like token theft and develop ML solutions to address them
• Apply advances in deep learning to improve model quality and detection rates at scale
• Co-build new fraud and abuse products directly with top users

Who you are

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

• 6+ years of industry experience training, evaluating, and deploying ML models in a production environment
• Proficiency in Python and common data and ML frameworks like SQL, Spark, and PyTorch
• Strong knowledge of production ML systems; and data analysis, statistics, and experiment design fundamentals
• Active interest in the latest ML developments, and how they can be leveraged to solve business problems

Preferred Qualifications

• Experience building and optimizing real-time, low-latency ML infrastructure at scale
• Strong software engineering skills and ability to design ML solutions through entire product stack
• Experience applying ML to fraud detection, risk modeling, or a closely related domain
• Experience designing ML products used by millions of users

Hybrid work at Stripe

This role is available either in an office or a remote location (35+ miles or 56+ km from a Stripe office).

In-office expectations

Office-assigned Stripes spend at least 50% of the time in a given month in their local office or with users. This hits a balance between bringing people together for in-person collaboration and learning from each other, while supporting flexibility about how to do this in a way that makes sense for individuals and their teams.

Working remotely at Stripe

A remote location is defined as being 35 miles (56 kilometers) or more from one of our offices. While you would be welcome to come into the office for team/business meetings, on-sites, meet-ups, and events, our expectation is you would regularly work from home rather than a Stripe office. Stripe does not cover the cost of relocating to a remote location. We encourage you to apply for roles that match the location where you currently live or plan to live.

Pay and benefits

The annual US base salary range for this role is $212,000 - $318,000. For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role. This salary range may be inclusive of several career levels at Stripe and will be narrowed during the interview process based on a number of factors, including the candidate’s experience, qualifications, and location. Applicants interested in this role and who are not located in the US may request the annual salary range for their location during the interview process.

• Additional benefits for this role may include: equity, company bonus or sales commissions/bonuses; 401(k) plan; medical, dental, and vision benefits; and wellness stipends.

We look forward to hearing from you.

At Stripe, we welcome diverse perspectives and people who think rigorously and aren't afraid to challenge assumptions. Join us.

The application window will remain open for 100 days after the Job Post is published. However, this opportunity will remain open based on the needs of the business, which may cause the application window to close before or after the 100-day mark.