As an Anti-Spoofing/Liveness Detection Engineer, you will help design and develop advanced systems to detect and prevent spoofing attacks in biometric authentication.
You will apply machine learning and deep learning to distinguish genuine interactions from fraudulent ones, ensuring secure and accessible digital experiences for all users.
Design and develop liveness detection systems using AI algorithms to separate real from fake biometric data, analyzing features such as facial characteristics, eye movements, and other physiological signals.
Build and optimize deep learning models tailored for liveness detection, selecting and refining algorithms to achieve high accuracy and reliability.
Engage in feature engineering by identifying and extracting important patterns from biometric data, including texture analysis, motion-based detection, and 3D depth analysis.
Work with data scientists and team members to collect, clean, and prepare large datasets for model training, ensuring data quality and representativeness.
Implement machine learning algorithms to process real-time biometric data, integrating multiple modalities like facial recognition, fingerprint scanning, and iris recognition.
Test and validate liveness detection systems thoroughly to ensure strong performance in real-world situations and validate models against a variety of spoofing techniques.
Deploy, monitor, and maintain liveness detection systems in production, ensuring scalability and high performance.
Proactively identify and address any accuracy or efficiency issues.
Requirements
Understanding of machine learning frameworks such as TensorFlow, Keras, or PyTorch.
Experience developing deep learning models.
Programming skills in Python, Java, or R (or similar languages) for model development and algorithm implementation.
Strong analytical and problem-solving abilities, with a familiarity with statistics, probability, and data analysis techniques.
Ability to work collaboratively with cross-functional teams—including data scientists, software engineers, and product managers—to achieve shared goals.
Preferred, but Not Required: Experience in anti-spoofing or biometric security systems.
Preferred, but Not Required: Familiarity with standards such as NIST ISO/IEC 30107 or FIDO.
Preferred, but Not Required: A passion for continuous learning and keeping up with the latest advancements in AI and machine learning.
Benefits
We are committed to creating an accessible and supportive workplace.
If you need reasonable accommodation(s) to participate in the application process or to perform this job, please let us know.
We value every candidate’s potential and welcome applications from all qualified individuals, including those from underrepresented and non-traditional backgrounds.
Applicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.