Description

You will secure GenAI systems by designing testing approaches to identify security flaws in confidentiality, integrity, and availability.

This role is on-site.

Responsibilities

• Design and implement security reference architectures and controls specifically for GenAI technologies.
• Conduct full-stack architecture reviews and security assessments, including maintaining threat models for GenAI platforms.
• Perform model input and output security testing, focusing on prompt injection and security assurance.
• Execute functional, regression, performance, and usability testing to evaluate AI algorithm behavior.
• Collaborate with data science and engineering teams to identify vulnerabilities and develop mitigation strategies.

Required Skills

• 12+ years of hands-on experience in cybersecurity or information security.
• 4+ years of advanced programming experience with Python and the standard ML stack (TensorFlow, PyTorch, NumPy, Pandas).
• 4+ years of experience working in cloud environments including Azure, AWS, or GCP.
• Proficiency in AI/ML fundamentals, including deep learning, NLP, and computer vision.
• Demonstrated expertise in attacking GenAI products and platforms.
• Recent experience working with Large Language Models (LLMs).
• Ability to write test scripts and automate test cases using Python and ML frameworks.

Preferred Skills

• Bachelor's degree in Computer Science, Electrical/Computer Engineering, Statistics, Econometrics, or equivalent experience.
• Experience assessing AI systems for ethical considerations, potential biases, and inclusivity.
• Overseeing the collection, preprocessing, and validation of training and testing datasets.

Key Skills

Education

Bachelor's degree