Lead applied research to develop next-generation fraud models over relational graphs, sequential events, images, and videos data.
Design and run rigorous experiments and develop evaluation methodologies that reflect real-world fraud dynamics.
Prototype state-of-the-art model architectures (Graph Neural Networks, Transformer-based foundation models) and translate successful prototypes into production with fellow MLEs.
Publish and communicate results internally and externally raising the technical bar for fraud ML at Plaid.

Requirements

PhD strongly preferred; we will consider equivalent research experience with a strong publication/innovation track record
3+ years of experience as a Machine Learning Engineer or Research Scientist
Strong scientific rigor and communication
Strong Python skills + ability to build high-quality research prototypes
Fraud / security / abuse domain experience - Nice to have
Experience with large-scale training, graph systems, and sequential modeling - Nice to have

Benefits

reasonable accommodations for candidates with disabilities in our recruiting process

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

PythonGraph Neural NetworksTransformer-based modelslarge-scale trainingsequential modelingevaluation methodologiesrigorous experimentsmodel architecturesprototypingproduction deployment

Soft Skills

scientific rigorcommunication

Certifications

PhD