Machine Learning Engineer, Credit Risk

Who we areAbout 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.

Machine Learning at Stripe

Machine learning is an integral part of almost every service at Stripe. Key products and use-cases powered by ML at Stripe include merchant and transaction risk, payments optimization and personalization, identity verification, and merchant data analytics and insights. We are also using the latest generative AI technologies to re-imagine product experiences, and are developing AI Assistants both for our customers and to make Stripes more productive across Support, Marketing, Sales, and Engineering roles within the company.

Stripe handles over $1T in payments volume per year, which is roughly 1% of the world’s GDP. We process petabytes of financial data using our ML platform to build features, train models, and deploy them to production. We use a combination of highly scalable and explainable models such as linear/logistic regression and random forests, along with the latest deep neural networks from transformers to LLMs. Some of our latest innovations have been around figuring out how best to bring transformers and LLMs to improve existing models and enable entirely new product ideas that are only made possible by GenAI. Stripe’s ML models serve millions of users daily and reduce financial risk, increase payment success rate, and grow the GDP of the internet. We work on challenging problems with large business impact, and seek to foster creativity and innovation.

What you’ll do

Stripe’s mission is to build the economic infrastructure for the internet.  Credit Detection brings together machine learning with product development to lower Stripe’s credit risk at scale, while retaining a best in class user experience.  Achieving this goal is critical to Stripe’s long term growth and profitability. We protect Stripe’s brand while also protecting the company from credit losses that can put our financial position at risk.

The Credit Detection team consists of machine learning engineers who want to tackle this problem through creative new product ideas and impactful machine learning models. We work closely with our credit partners in product, business, data science, and operations to prioritize and drive our shared strategy. We are continuously exploring and undertaking new ideas and as an Engineering Manager you can have an outsized impact on the future of how Stripe manages risk at scale. 

As a machine learning engineer, you will be responsible for designing, building, training, evaluating, deploying, and owning ML models in production. You will work closely with software engineers, machine learning engineers, product managers, and data scientists to operate Stripe’s ML powered systems, features, and products. You will also have the opportunity to contribute to and influence ML architecture at Stripe and be a part of a larger ML community.

Responsibilities

• Design state-of-the-art ML models and large scale ML systems for detection and decisioning for Stripe products based on ML principles, domain knowledge, and engineering constraints
• Experiment and iterate on ML models (using tools such as PyTorch, TensorFlow, and XGBoost) to achieve key business goals and drive efficiency
• Develop pipelines and automated processes to train and evaluate models in offline and online environments
• Integrate ML models into production systems and ensure their scalability and reliability
• Collaborate with product and strategy partners to propose, prioritize, and implement new product features
• Engage with the latest developments in ML/AI and take calculated risks in transforming innovative ML ideas into productionized solutions
•  

Who you are

We are looking for ML Engineers who are passionate about building ML systems that touch the lives of millions. You have experience developing efficient feature pipelines, building advanced ML models, and deploying them to production. You are comfortable with ambiguity, love to take initiative, have a bias towards action, and thrive in a collaborative environment.

Minimum requirements

• 2+ years of industry experience building and shipping ML systems in production
• Proficient with ML libraries and frameworks such as PyTorch, TensorFlow, XGBoost, as well as Spark 
• Knowledge of various ML algorithms and model architectures
• Hands-on experience in designing, training, and evaluating machine learning models
• Hands-on experience in productionizing and deploying models at scale
• Hands-on experience in orchestrating complicated data pipelines and efficiently leveraging large-scale datasets

Preferred qualifications

• MS/PhD degree in ML/AI or related field (e.g. math, physics, statistics)
• Experience with DNNs including the latest architectures such as transformers and LLMs
• Experience working in Java or Ruby codebases
• Proven track record of building and deploying ML systems that have effectively solved ambiguous business problems
• Experience in adversarial domains such as Payments, Fraud, Trust, or Safety