Machine Learning Engineer, Link

Stripe

New York, NY

On-site

Who this role is best for

Geared toward experienced machine learning engineers comfortable with real-time risk decisioning and fraud detection systems.

Best fit for

Experienced ML engineers with a track record in adversarial domains like fraud detection or identity verification
— “Experience applying machine learning to fraud detection, risk modeling, payment authorization, identity, account security, or another adversarial domain.”
Candidates who have owned end-to-end ML systems from analysis to deployment and iteration
— “Demonstrated ability to take an open-ended business problem, determine where machine learning can help, and own the solution through production.”
Individuals with strong data engineering and system design experience for production ML
— “Design data pipelines, features, evaluation methods, experiments, and monitoring systems that support reliable production models.”

Things to consider

The role demands full ownership of ambiguous problems through implementation and measurement
— “Own ambiguous problems from initial analysis and problem definition through technical design, implementation, launch, measurement, and iteration.”
This position requires working with large-scale datasets and real-time systems
— “Experience building real-time, low-latency machine learning or risk decisioning systems at scale.”

How to stand out

Highlight experience in deploying ML solutions in production environments, especially for fraud detection
— “Build, train, evaluate, deploy, and own machine learning models that detect fraud and abuse across Link.”
Emphasize your ability to define and own technical direction for ML systems in partnership with cross-functional teams
— “Define technical direction in partnership with Engineering, Product, and Data Science.”
Showcase your work with complex datasets and statistical analysis to solve business problems
— “Use large-scale datasets to investigate emerging threats, develop hypotheses, and identify opportunities to improve payment performance.”
Demonstrate your experience with model evaluation, monitoring, and iteration in production systems
— “Strong knowledge of production machine learning systems, including data pipelines, feature development, model evaluation, deployment, monitoring, and iteration.”
Demonstrate your ability to integrate models into production services and build reliable systems around outputs
— “Experience integrating models into production services and designing reliable systems around model outputs.”

Pace · Fast PacedCollaboration · HighAutonomy · MediumDecision Impact · Team

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

model deployment
fraud prevention
risk management

Typical background

machine learningfraud detectionrisk management

Skills & requirements

Required

Fraud DetectionMachine Learning ModelsRisk Decisioning SystemsData Pipelines

Preferred

Link Payment Methods Knowledge

Stack & domain

Machine LearningFraud DetectionRisk ModelingCollaborationProblem-solvingPaymentsFintechDigital Wallets

About the role

Original posting from Stripe

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
Link is a digital wallet designed for fast and secure online payments. It allows consumers to save and use their preferred payment methods across the Link network, helping them check out quickly and securely wherever Link is accepted.
The Link Fraud and Auth team works to make Link the most trusted and highest-performing way to pay. We protect consumers and merchants from fraud, abuse, and financial loss while maximizing authorization rates for good users. Our work spans consumer-facing experiences, payment infrastructure, and ML powered risk systems.
We manage fraud and financial risk across a growing range of novel Link features, including Link’s agentic wallet, stored balance, and LPMs. The team also owns Instant Bank Payments, a proprietary payment method built on ACH rails, offering merchants immediate confirmation while protecting them from bank-initiated returns. IBP is the heart of Link’s revenue engine, giving LFA engineers the opportunity to shape and scale one of Link’s most important products.
What you’ll do
As a machine learning engineer on Link Fraud and Auth, you’ll build and operate models and risk decisioning systems that protect Link while helping more legitimate payments succeed. You’ll work across the full machine learning lifecycle, from analyzing fraud patterns and identifying opportunities to building, deploying, monitoring, and improving models in production. You’ll use data to form hypotheses, make practical modeling choices, and define technical direction in partnership with Engineering, Product, and Data Science. Your work will directly influence Link’s fraud performance, authorization rates, and ability to expand into new products and payment experiences.
Responsibilities
Build, train, evaluate, deploy, and own machine learning models that detect fraud and abuse across Link.
Use large-scale datasets to investigate emerging threats, develop hypotheses, and identify opportunities to improve payment performance.
Develop pragmatic machine learning solutions, including tree-based models and other approaches suited to real-time risk decisioning.
Design data pipelines, features, evaluation methods, experiments, and monitoring systems that support reliable production models.
Build and improve risk decisioning systems that integrate with other parts of Stripe’s payments stack.
Own ambiguous problems from initial analysis and problem definition through technical design, implementation, launch, measurement, and iteration.
Collaborate with Engineering, Product, Data Science, and Risk partners across Stripe to turn model improvements into durable product outcomes.
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 building and shipping machine learning models in production.
Strong programming skills in Python and experience with common data and machine learning tools, such as SQL, Spark, and XGBoost.
Strong knowledge of production machine learning systems, including data pipelines, feature development, model evaluation, deployment, monitoring, and iteration.
Experience working with large and complex datasets and applying data analysis, statistics, and experimentation fundamentals.
Demonstrated ability to take an open-ended business problem, determine where machine learning can help, and own the solution through production.
Strong judgment in selecting practical modeling approaches and evaluating tradeoffs among model performance, system complexity, latency, and business impact.
Strong collaboration skills and the ability to work across teams and contribute to peers' success.
Preferred qualifications
Experience applying machine learning to fraud detection, risk modeling, payment authorization, identity, account security, or another adversarial domain.
Experience building real-time, low-latency machine learning or risk decisioning systems at scale.
Experience integrating models into production services and designing reliable systems around model outputs.
Experience with payments, fintech, digital wallets, or money movement.
Strong software engineering skills and experience designing solutions across the machine learning and product stack.

Source: Stripe careers