Machine Learning Engineer (Deepfake & Injection Attack Detection / Face Liveness)

Machine Learning Engineer

Mitek is a global leader in digital identity verification, biometric authentication, and fraud prevention. Our AI-powered platform combines computer vision, biometrics, and machine learning to help organizations securely onboard users and defend against emerging threats such as deepfakes and AI-driven fraud.

Trusted by over 7,500 organizations worldwide, Mitek processes millions of identity transactions daily. Headquartered in San Diego, with a strong presence across Spain, France, Mexico, and the UK and the Netherlands. We are driven by a clear mission: protect what's real.

At Mitek, we believe that teams are more resilient, effective, and innovative when they benefit from a wide range of ideas, lived experiences, and perspectives. The strength of our organization is deeply rooted in the people who power it.

We are a Virtual First organization that values flexibility, collaboration, and innovation, while fostering an inclusive environment where diverse perspectives drive better outcomes.

Why Join This Team

• Work on AI that fights AI-driven fraud
• Direct impact on protecting users from real-world threats
• Collaborate with experts across fraud, biometrics, and AI research
• Opportunities for growth across teams and domains within Mitek
• A culture focused on collaboration, innovation, and continuous learning

The Impact You'll Make

As a Machine Learning Engineer, you will join our Fraud & AI Integrity group, specifically focused on deepfake detection, digital manipulation, and injection attack detection in selfie-based identity verification.

This is a hands-on, production-focused role where you will design and deploy computer vision models that operate in adversarial environments. Your work will directly contribute to protecting users and businesses from sophisticated fraud attacks powered by AI.

What You Will Do (Core Responsibilities):

• Design, train, and deploy machine learning models for image-based fraud detection, including:
• Deepfake detection
• Injection attack detection
• Digital manipulation analysis in biometric verification
• Work end-to-end across the ML lifecycle:
• Dataset curation (large-scale, noisy, adversarial datasets)
• Model development and training
• Evaluation and iteration using fraud-relevant metrics
• Production deployment and monitoring
• Build robust data pipelines, including:
• Data validation, cleaning, and labeling strategies
• Handling class imbalance, bias, and distribution shift
• Define and execute evaluation frameworks focused on real-world performance:
• Precision/recall trade-offs
• False positive vs. fraud detection balance
• Robustness to unseen attack types
• Collaborate closely with:
• Fraud & AI research teams
• Data collection and annotation teams
• MLOps and platform engineering
• Product teams
• Contribute to production ML systems, ensuring:
• Scalability and reliability
• Monitoring and performance tracking
• Continuous improvement against evolving threats

Who You Are (Soft Skills):

• A pragmatic problem-solver who understands the gap between research and production
• Comfortable working in adversarial, fast-evolving problem spaces
• Able to clearly communicate technical concepts and trade-offs
• Collaborative and adaptable, with a strong sense of ownership
• Motivated by building technology that has real-world impact

What You Need (Required Knowledge, Technical Skills):

• Bachelor's degree in Computer Science, Engineering, or related field
• 2+ years of experience deploying machine learning models into production
• Strong background in computer vision (image-based ML)
• Solid programming skills in Python
• Hands-on experience with PyTorch and/or TensorFlow
• Experience working with real-world datasets and building data pipelines

Tech Stacks

• Cloud: AWS
• Languages: Python
• ML Frameworks: PyTorch, TensorFlow, Scikit-learn
• Data Tools: Pandas, OpenCV
• Infrastructure: Docker, CI/CD, cloud-based ML pipelines

What Would be Nice (Preferred Experience):

• Advanced degree (PhD or equivalent experience in Machine Learning or Computer Vision)
• Experience in fraud detection or adversarial ML domains
• Experience with deepfake detection, image forensics, or manipulation detection
• Familiarity with generative AI models (training or analysis)
• Background in data science or data engineering

What We Provide (Benefits):

• Competitive package
• Full Remote contract
• Annual Leave
• Home Office Allowance
• Annual Bonus – up to 10%
• Health Insurance
• Learning & Development: We promote continuous learning and support role-aligned development opportunities, with access to a complimentary LinkedIn Learning licence.

€50,000 - €75,000 a year Working Model Remote within Spain Occasional in-person collaboration (weekly or biweekly is a plus)

We take pride in enabling career growth in an environment of innovation and teamwork.

Our commitment to all Mitekians is to do meaningful work that matters. Our culture is defined by delivering our best to our customers by providing high value solutions and impactful outcomes, by continuously challenging convention, and by caring for each other through collaboration and celebrating our successes. We are committed to creating competitive, equitable compensation & benefits programs and career development opportunities.

We sincerely appreciate your interest in Mitek. We know your time is valuable and look forward to the potential of speaking with you further!