Senior Machine Learning Engineer, Fraud ML

This is a fully remote position, open to applicants in Canada.

📋 Description

• You will spearhead the development of innovative fraud prediction models utilizing a combination of methods for tabular, graph, and behavioral data.

• You will construct and scale feature pipelines and training datasets from both proprietary and third-party signals, collaborating with data and platform teams as necessary.

• You will prototype new modeling concepts and features, conduct offline experiments, and implement the best-performing methods into production with suitable risk controls.

• You will productionize models by integrating them into batch and/or real-time decision-making systems, enhancing reliability, latency, and operational robustness.

• You will monitor and assess model and data health, while also aiding in the definition of retraining and backtesting workflows as fraud patterns change.

• You will identify and execute foundational enhancements to the team's model-building processes.

• Collaboration across Engineering, Fraud Analytics, Product, and ML Platform will be essential to define requirements, assess tradeoffs, and clearly communicate results to both technical and non-technical audiences.

⛳️ Requirements

• A minimum of 6 years of experience in researching, training, tuning, and deploying ML models at scale; a relevant PhD may account for up to 2 years of this experience.

• Proven history of delivering high-impact machine learning models in a low-latency, live environment.

• Proficient in Python with experience in writing production-quality code.

• Experience in building and evaluating models for tabular classification tasks, preferably using gradient-boosted decision trees like LightGBM, XGBoost, CatBoost, or similar.

• Familiarity with a deep learning framework, with a preference for PyTorch.

• Experience in working with distributed data processing or parallel computing frameworks, preferably Spark, Ray, Dask, or similar.

• Knowledge of ML lifecycle tools for training orchestration, experimentation, and model monitoring (e.g., Kubeflow, Airflow, MLflow, or equivalent internal platforms).

• Skilled in utilizing AI-powered developer tools (e.g., Claude Code, Cursor, or similar) to enhance iteration, debugging, and code quality as part of daily development activities.

• Proven ability to transform simple problems or business scenarios into solutions that engage multiple software components, executing by writing clear, comprehensible, well-tested, and extendable code.

• Comfort in navigating extensive codebases, debugging others' code, and providing constructive feedback to peers through code reviews.

• Demonstrated ownership of personal growth by actively seeking feedback from your team, manager, and stakeholders.

• Strong verbal and written communication skills that facilitate effective collaboration with our global engineering team.

🏝️ Benefits

• Health care coverage - Affirm covers all premiums for all levels of coverage for you and your dependents.

• Flexible Spending Wallets - generous stipends to spend on Technology, Food, various Lifestyle needs, and family formation expenses.

• Time off - competitive vacation and holiday schedules that allow you to take time off to rest and recharge.

• ESPP - An employee stock purchase plan that enables you to acquire shares of Affirm at a discounted rate.