Senior Machine Learning Engineer (Fraud)

TL;DR

Senior Machine Learning Engineer (Fraud): Building and optimizing machine learning systems for cutting-edge fraud detection products with an accent on scalable ML infrastructure and model deployment. Focus on leading applied research, developing next-generation fraud models, and ensuring high reliability and performance at scale.

Location: Remote (USA) or Hybrid in San Francisco, New York, Seattle, Washington D.C.

Salary: $225,600–$337,200 a year

Company

hirify.global is a financial technology company dedicated to empowering financial transformation by building tools and experiences for thousands of developers to create their own products.

What you will do

• Lead applied research to develop next-generation fraud models using relational graphs, sequential events, images, and video data.
• Design and run rigorous experiments and develop evaluation methodologies reflecting real-world fraud dynamics.
• Prototype state-of-the-art model architectures (Graph Neural Networks, Transformer-based foundation models) and translate successful prototypes into production.
• Publish and communicate research results internally and externally to raise the technical bar for fraud ML.

Requirements

• PhD strongly preferred; equivalent research experience with a strong publication/innovation track record will be considered.
• 3+ years of experience as a Machine Learning Engineer or Research Scientist.
• Strong scientific rigor and communication skills.
• Strong Python skills and ability to build high-quality research prototypes.

Nice to have

• Fraud / security / abuse domain experience.
• Experience with large-scale training, graph systems, and sequential modeling.

Culture & Benefits

• Unlock financial freedom for everyone by building a diverse team committed to making the financial ecosystem more equitable.
• Committed to providing reasonable accommodations for candidates with disabilities during the recruiting process.
• Proud to be an equal opportunity employer valuing diversity across various protected characteristics.