Senior ML Engineer — Scalable Fraud Detection Systems

Plaid; United States; On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Office locations SF

Office locations NYC

Office locations Raleigh-Durham

Health benefits

Fertility support

Mental health support

Parental leave

Home office stipend

Daycare support

Commuting benefits

Job summary

Plaid is seeking a Senior Machine Learning Engineer to own the development of high-performance feature computation and online inference pipelines powering production ML systems at scale. You will build observability, monitoring, and automated debugging capabilities, while leveraging AI-assisted tools to investigate complex system behavior and maintain high reliability.

You will partner with ML Infrastructure, Data Science, and Product teams to execute critical technical initiatives and deliver

Qualifications

• 6+ years of relevant experience in ML systems.
• Proficiency with Python and ML tech such as PyTorch, Spark, SageMaker, Airflow.
• Ability to independently own end-to-end ML engineering projects in production.
• Strong experience with ML infrastructure, production deployment, monitoring, and reliability.
• Experience in Graph machine learning and fraud/risk domains.

Responsibilities

• Own development of feature computation and online inference pipelines for production ML systems.
• Build observability, monitoring, and automated debugging capabilities.
• Collaborate with ML Infrastructure, Data Science, and Product teams on critical initiatives.
• Scale ML systems for a growing fraud detection product in a fast-paced environment.
• Solve complex challenges at the intersection of ML, data infra, and production reliability.
• Develop foundational ML capabilities leveraging Plaid’s data to detect and prevent fraud.

Skills

Python

PyTorch

Spark

SageMaker

Airflow

Graph ML

Fraud/Risk

Production Deployment

Monitoring

End-to-End ML Projects

Job description

Plaid is seeking a Senior Machine Learning Engineer to own the development of high-performance feature computation and online inference pipelines powering production ML systems at scale. You will build observability, monitoring, and automated debugging capabilities, while leveraging AI-assisted tools to investigate complex system behavior and maintain high reliability.

You will partner with ML Infrastructure, Data Science, and Product teams to execute critical technical initiatives and deliver