高级机器学习工程师（欺诈）
Senior Machine Learning Engineer (Fraud)
在Affirm，我们为那些重要的时刻而存在——为人们提供一种清晰、可预测的分期付款方式，没有隐藏费用，没有意外，也不会在最重要的事情上做出妥协。
在机器学习反欺诈团队中，你将构建和改进机器学习系统，以实现实时交易决策，保护消费者和商家，同时平衡欺诈损失、客户体验和转化率。你将与经验丰富的机器学习工程师、平台合作伙伴和跨职能利益相关者紧密合作，将模型从想法转化为原型，再部署到生产环境，并随着欺诈模式的变化持续进行强有力的度量和监控。
你将负责的工作
- 你将主导使用表格、图和行为数据的混合方法开发新的欺诈预测模型
- 你将构建并扩展特征管道和训练数据集，从专有和第三方信号中获取数据，在需要时与数据和平台团队合作。
- 你将对新的建模思路和特征进行原型设计，运行离线实验，并将表现最佳的方法带入生产环境，同时设置适当的风险控制。
- 你将实现模型的生产化：集成到批量和/或实时决策系统中，并提升可靠性、延迟和操作稳健性。
- 你将对模型和数据健康状况进行监控和仪表化，并帮助定义重新训练/回测流程，以应对欺诈模式的变化。
- 识别并实施团队构建模型的基础性改进。
- 你将与工程、欺诈分析、产品和机器学习平台团队合作，定义需求，评估权衡，并向技术及非技术人员清晰地传达结果。
我们寻找的人选
- 你有6年以上在大规模场景下研究、训练、调优和发布机器学习模型的经验。相关博士学历最多可算作2年经验。
- 在低延迟的实时环境中交付高影响力机器学习模型的记录。
- 强大的Python技能和编写生产级代码的经验。
- 有构建和评估表格分类问题模型的经验（优先考虑梯度提升决策树如LightGBM/XGBoost/CatBoost，或其他类似模型）。
- 有使用深度学习框架的经验（PyTorch优先）。
- 有使用分布式数据处理或并行计算框架的经验（Spark优先；Ray/Dask或其他类似框架）。
- 有使用机器学习生命周期工具的经验，用于训练编排、实验和模型监控。
查看英文原文
At Affirm, we exist for the moments that matter—giving people a clear, predictable way to pay over time, with no hidden fees, no surprises, and no tradeoffs on what matters most.
On the ML Fraud team, you’ll build and improve machine learning systems that make real-time transaction decisions, protecting consumers and merchants while balancing fraud loss, customer experience, and conversion. You’ll work closely with experienced ML engineers, platform partners, and cross-functional stakeholders to take models from idea to prototype to production, and to keep them healthy with strong measurement and monitoring as fraud patterns evolve.
What you’ll do
- You will lead development of new fraud prediction models using a mix of approaches for tabular, graph, and behavioral data
- You will build and scale feature pipelines and training datasets from proprietary and third-party signals, partnering with data and platform teams when needed.
- You will prototype new modeling ideas and features, run offline experiments, and drive the best-performing approaches into production with appropriate risk controls.
- You productionize models: integrate into batch and/or real-time decision systems, and improve reliability, latency, and operational robustness.
- You will instrument and monitor model and data health, and help define retraining/backtesting workflows as fraud patterns evolve.
- Identify and implement foundational improvements to how the team builds models.
- You will collaborate across Engineering, Fraud Analytics, Product, and ML Platform to define requirements, evaluate tradeoffs, and communicate results clearly to both technical and non-technical audiences.
What we look for
- You have 6+ years experience researching, training, tuning and launching ML models at scale. Relevant PhD can count for up to 2 years of experience.
- Track record of delivering high impact machine learning models in a low latency live setting
- Strong Python skills and experience writing production-quality code.
- Experience building and evaluating models for tabular classification problems (preferably gradient-boosted decision trees like LightGBM/XGBoost/CatBoost, or similar).
- Experience with a deep learning framework (PyTorch preferred).
- Experience working with distributed data processing or parallel compute frameworks (Spark preferred; Ray/Dask or similar).
- Experience with ML lifecycle tooling for training orchestration, experimentation, and model monitoring (e.g., Kubeflow, Airflow, MLflow, or equivalent internal platforms).
- Proficient in using AI-powered developer tools (e.g., Claude Code, Cursor, or similar) to accelerate iteration, debugging, and code quality as part of day-to-day development workflows.
- You have mastered taking a simple problem or business scenario into a solution that interacts with multiple software components, and executing on it by writing clear, easily understood, well tested and extensible code.
- You are comfortable navigating a large code base, debugging others' code, and providing feedback to other engineers through code reviews.
- Your experience demonstrates that you take ownership of your growth, proactively seeking feedback from your team, your manager, and your stakeholders.
- You have strong verbal and written communication skills that support effective collaboration with our global engineering team.
Pay Grade - N
Equity Grade - 6
Employees new to Affirm typically come in at the start of the pay range. Affirm focuses on providing a simple and transparent pay structure which is based on a variety of factors, including location, experience and job-related skills.
Base pay is part of a total compensation package that may include monthly stipends for health, wellness and tech spending, and benefits (including 100% subsidized medical coverage, dental and vision for you and your dependents). In addition, the employees may be eligible for equity rewards offered by Affirm Holdings, Inc. (parent company).
CAN base pay range per year: $153,000 - $213,000
Location - Remote Canada
This remote role is open only to candidates residing in Alberta, British Columbia, Manitoba, New Brunswick, Newfoundland and Labrador, Nova Scotia, Ontario, Prince Edward Island, or Saskatchewan.
#LI-Remote
Remote-first with flexibility built in
Affirm is proud to be a remote-first company. Most roles can be done from almost anywhere within the country of employment. Some positions may occasionally require in-person work at an Affirm office, and a few are office-based due to the nature of the work. All new hires will be invited to attend an in-person onboarding experience.
Benefits designed for you
Our benefits reflect our commitment to care, transparency, and flexibility. Here are a few highlights:
- Health coverage at no cost: We cover 100% of premiums for employees and their dependents.
- Spending stipends: Monthly stipends support your tech setup, and the ability to choose health and wellness options that are right for you.
- Time off to recharge: Flexible time off and generous holiday calendars help you rest when you need to.
- Own a piece of what you build: Our employee stock purchase plan (ESPP) lets you buy Affirm stock at a discount.
We’re committed to providing an inclusive interview process, including accommodations for candidates with disabilities. If you need support, we’re happy to help.
For positions based in San Francisco or Los Angeles: Affirm considers qualified applicants with arrest and conviction records, as required by law.
By clicking "Submit Application," you acknowledge that you have read Affirm's Global Candidate Privacy Notice and consent to the use of your personal information as described.