Plaid's Fraud Data team builds machine learning systems for fraud detection products, leveraging network data to prevent fraud proactively. The Staff Machine Learning Engineer will design and build scalable ML infrastructure for this product, leading the evolution of model deployment, monitoring, and observability frameworks.
Requirements
- 8+ years total experience, with at least 5 years building and deploying production ML systems.
- Proven experience in machine learning infrastructure/operations.
- Demonstrated technical leadership and architectural vision, driving systems from concept to production.
- Proficiency in Python, PyTorch, Spark, SageMaker, and Airflow, or equivalent technologies.
- experience working in fraud detection, risk modeling, or financial security domains.
- background in graph machine learning or related techniques.
Responsibilities
- Design and build scalable ML infrastructure for Plaid’s fraud detection product
- Lead the evolution of our model deployment, monitoring, and observability frameworks to ensure high reliability and performance at scale
- Collaborating closely with teams across ML Infrastructure, Product, and Engineering, you’ll deliver robust systems that protect users and customers from fraud
- Mentor other engineers and help shape the long-term technical vision and strategy of the Fraud Data team
- Working at a fast-pace environment to build a rapidly growing product with a championship team
- Solving complex problems at the intersection of ML systems, data, and reliability
- Building the foundations for fraud detection on the largest financial dataset in the world
Other
- Working at a fast-pace environment
- Collaborating with talented engineers and data scientists across Plaid
- We believe that the way people interact with their finances will drastically improve in the next few years.
- We’re dedicated to empowering this transformation by building the tools and experiences that thousands of developers use to create their own products.
- We encourage you to apply to a role even if your experience doesn't fully match the job description.
