Position: Security Engineer - Offensive Al / GenAl Security

Location; Mountain View, CA

Duration: 6+ Months Contract

Job Summary:

We are looking for a seasoned Security Engineer specializing in Offensive Al and Generative Al Security to join our team. With over 5 years of experience in penetration testing, vulnerability management, and Al/ML security practices, the ideal candidate will possess robust expertise in both manual and automated security testing methods tailored for Al-driven systems. This role demands deep technical know-how in developing and utilizing tools for offensive security testing specifically focused on Al and machine learning models.

Responsibilities:

Execute hands-on penetration testing and security assessments on Generative Al Applications, Al/ML components, Web Applications, Web Services and integrated systems to pinpoint vulnerabilities.

Lead the development of security utilities and tools designed to automate offensive security testing of Al-models and Generative Al ecosystems.

Engineer and automate comprehensive security testing procedures for Generative Al platforms using programming skills in Python, Perl, and Bash.

Utilize advanced knowledge of OWASP, SANS25, CVE, and MITRE alongside specific Al-related security frameworks to guide in-depth security assessments and threat modeling.

Collaborate with Al model developers and data scientists to understand Al architectures and develop tailored security practices and tools.

Conduct systematic vulnerability management programs specifically designed around Al and Generative Al technologies, ensuring meticulous execution, reporting, and follow-up remediations.

Develop security assessment methodologies, procedures, and testing suites that are specifically crafted for Al and machine learning environments.

Stay abreast of the latest in security, Al developments, and threats, integrating fresh insights into security strategies and test designs.

Manage and lead security review processes for third-party Al vendors and technology partners, ensuring adherence to our stringent security standards and protocols.

Adopt and adapt existing penetration testing tools, as well as develop proprietary tools necessary for effective Offensive Al security testing.

Work dynamically across various teams including product development and Al development groups, ensuring a complete and unified approach to Al Security.

Document and report on security findings, challenges, and progress in a comprehendible and detailed manner suited for both Al specialists and non-specialist stakeholders.

Identify and drive the implementation of best practices and security solutions

Requirements:

Bachelor's or Master's degree in Computer Science, Information Security, AI/ML, or a related technical field.

Minimum of 5 years of experience in penetration testing and vulnerability management including substantial exposure to AI/ML or Generative Al specific security testing.

Demonstrable experience in both manual and automated offensive security tactics.

Proficient in developing and implementing security tools and processes for Generative Al security testing environments.

Deep understanding of authentication protocols, data integrity checks, and secure data handling specific to AI/ML models.

Technical fluency in Al technologies, including experience with Generative AI models, Machine Learning techniques, and prompt engineering (OpenAl, Google Gemini, Claude etc.)

Strong programming skills in Python, Perl, Bash, or similar languages, with specific tools development expertise for Al security.

Outstanding communication and presentation skils to effectively share insights and recommendations across technical and non-technical teams.

Critical thinking and advanced problem-solving skills dedicated to the Al security landscape.

Relevant certifications such as OSCP OSWE OSEP, CRTE, CRTP with added preference for Al-specific security training or credentials.