Real-Time Fraud ML Engineer | Production-Grade Systems

Q2; Austin (TX); Hybrid; USD 120,000 - 190,000; Full time

Benefits offered by this job

Hybrid Work

Flexible PTO

Career Development

Health Insurance

Parental Leave

Volunteer Programs

Job summary

Q2 is a leading provider of digital banking and lending solutions, enabling financial institutions to combat fraud at scale. The Machine Learning Engineer role focuses on building and operating production systems behind fraud detection, collaborating with data scientists and engineers to deliver real-time, reliable ML solutions that protect trillions in transactions yearly.

You will work across model development, evaluation, deployment, and monitoring, turning models into scalable applications,

Qualifications

• 2+ years of relevant ML experience and deployment
• Strong stats, experimentation, and modeling background
• Proficiency in Python and ML frameworks

Responsibilities

• Research emerging fraud patterns and translate into detection approaches
• Build next-gen ML products across identity, behavior, and transaction fraud
• Develop real-time, low-latency ML infrastructure and improve reliability
• Maintain training/evaluation/inference pipelines with data scientists
• Write clean, well-tested production code following best practices
• Monitor and troubleshoot production ML systems and pipelines

Skills

ML model development

Python

Statistics & experiments

Problem solving

Collaboration

Education

Bachelor's degree in related field

Tools

TensorFlow

PyTorch

scikit-learn

Cloud platforms

Job description

Q2 is a leading provider of digital banking and lending solutions, enabling financial institutions to combat fraud at scale. The Machine Learning Engineer role focuses on building and operating production systems behind fraud detection, collaborating with data scientists and engineers to deliver real-time, reliable ML solutions that protect trillions in transactions yearly.

You will work across model development, evaluation, deployment, and monitoring, turning models into scalable applications,