Senior Staff Machine Learning Engineer, (ml Underwriting)

Affirm Affirm · Fintech · Canada, United States · Remote · Checkout

Senior Staff Machine Learning Engineer at Affirm, focusing on ML Underwriting. This role involves defining and driving multi-year technical strategy for ML, leading the design, implementation, and scaling of advanced ML systems, and providing technical leadership and mentorship. The position requires extensive experience in deploying and operating large-scale, real-time ML systems, with a focus on representation learning, embedding-based modeling, and sequence modeling.

What you'd actually do

  1. You will define and drive multi-year, multi-team technical strategy for machine learning across Affirm, ensuring alignment with company-wide priorities and influencing the roadmaps of partner teams and platforms.
  2. You will lead the design, implementation, and scaling of advanced ML systems, setting the architectural direction for complex, cross-functional initiatives and ensuring systems remain reliable, extensible, and prepared for increasingly sophisticated modeling workloads.
  3. You will partner deeply with ML Platform, product, engineering, and risk leadership to shape long-term modeling capabilities, define new opportunities for ML impact, and guide infrastructure evolution required for next-generation ML methods.
  4. You will provide broad technical leadership across the ML organization, mentoring senior engineers, elevating design and code quality, and spreading ML expertise through documentation, talks, and cross-org guidance.
  5. You will drive clarity and alignment on ambiguous, high-stakes technical decisions, resolving cross-team tensions, balancing competing priorities, and exercising judgment optimized for the broader engineering organization.

Skills

Required

  • Python
  • PyTorch
  • XGBoost
  • Kubeflow
  • MLflow
  • Spark
  • Ray
  • representation learning
  • embedding-based modeling
  • neural network-based sequence modeling
  • Transformers
  • recurrent models
  • attention-based models
  • multi-task learning
  • large-scale distributed ML infrastructure
  • streaming data ingestion
  • batch data ingestion
  • feature stores
  • feature engineering
  • training pipelines
  • model serving
  • inference infrastructure
  • monitoring
  • automated retraining

Nice to have

  • PhD in a related field

What the JD emphasized

  • 10+ years of experience researching, designing, deploying, and operating large-scale, real-time machine learning systems
  • experience leading end-to-end ML system design, from data architecture and feature pipelines to model training, evaluation, and production deployment
  • deep hands-on experience with large-scale distributed ML infrastructure, including streaming or batch data ingestion, feature stores, feature engineering, training pipelines, model serving and inference infrastructure, monitoring, and automated retraining

Other signals

  • scaling advanced modeling approaches
  • elevate our modeling capabilities
  • ensure our systems can support increasingly sophisticated workloads
  • drive high-impact innovation