Base Salary
$153k - $213k/yr
Responsibilities
- Lead development of fraud prediction models using tabular, graph, and behavioral data.
- Build and scale feature pipelines and training datasets from proprietary and third-party signals.
- Prototype modeling ideas, run offline experiments, and move effective approaches into production with appropriate risk controls.
- Integrate models into batch and real-time decision systems while improving reliability, latency, and operational robustness.
- Instrument and monitor model and data health and help define retraining and backtesting workflows.
- Implement foundational improvements to the team’s model development processes.
- Collaborate with Engineering, Fraud Analytics, Product, and ML Platform to define requirements, evaluate tradeoffs, and communicate results.
Requirements
- 6+ years of experience researching, training, tuning, and launching machine learning models at scale; a relevant PhD can count for up to 2 years of experience.
- Track record of delivering high-impact machine learning models in low-latency live settings.
- Strong Python skills and experience writing production-quality code.
- Experience building and evaluating tabular classification models, preferably using gradient-boosted decision trees such as LightGBM, XGBoost, or CatBoost.
- Experience with a deep learning framework, preferably PyTorch.
- Experience with distributed data processing or parallel compute frameworks, preferably Spark, Ray, or Dask.
- Experience with ML lifecycle tooling for training orchestration, experimentation, and model monitoring, such as Kubeflow, Airflow, or MLflow.
- Proficiency with AI-powered developer tools such as Claude Code or Cursor.
- Ability to design solutions spanning multiple software components and implement clear, well-tested, extensible code.
- Ability to navigate large codebases, debug other engineers’ code, and provide code review feedback.
- Strong verbal and written communication skills for collaboration with global engineering teams.
Benefits
- Remote-first work arrangement in Canada, limited to specified provinces.
- Affirm covers 100% of medical, dental, and vision premiums for employees and dependents.
- Flexible spending wallets with stipends for technology, food, lifestyle, and family-forming expenses.
- Competitive vacation and holiday schedules.
- Employee stock purchase plan with discounted shares.
- Monthly health, wellness, and technology spending stipends may be available.
- Reasonable interview accommodations are available for candidates with disabilities.
Tech Stack
Categories
About Affirm
At Affirm, we’re using today’s technology to bring significant disruptive innovation to the financial industry. We focus on improving the lives of consumers by delivering simple, honest and transparent financial products. We have roles across a variety of teams, including engineering, product, finance, operations, revenue, marketing, people and more. A note to applicants: Fake job and recruiting scams are on the rise. Affirm will never ask you to pay any upfront fees or send you any checks to purchase equipment during any part of the recruiting process. Affirm only uses legitimate company email address domains (either “@affirm.com” or "@us.greenhouse-mail.io”) to communicate with candidates via email. Affirm is also proud to be a remote-first company! Attracting great people starts by finding talent in different places. That's why we built remote work into the DNA of how we do business—but if an office space is more your style, we have offices in Chicago, New York City, Pittsburgh, San Francisco, Seattle, Toronto, Warsaw, Madrid and London. Not to mention we have comprehensive and award-winning benefits that were made for you. Interested in learning more? Check out our careers page and apply today! Visit affirm.com/careers for more information.