Adversarial AI, Research Engineer

📋 Description

• Oversee adversarial testing of AI by conceptualizing, defining, and implementing red team evaluations against our AI ecosystem, utilizing a risk-based prioritization strategy to identify and mitigate vulnerabilities prior to exploitation.

• Pioneer innovative AI attack methods by merging cutting-edge academic insights with established offensive security practices to develop new Tactics, Techniques, and Procedures, ensuring that assessments remain in line with the latest advancements in the field.

• Develop and enhance security tools following an automation-first approach, leading efforts to integrate security testing earlier in the development process by distributing specialized tools to AI security stakeholders in Engineering, Research, and Ethics.

• Act as a strategic ally throughout the organization, offering an offensive security viewpoint to inform product development, aid corporate governance, and contribute to policies such as Salesforce's Generative AI Security Standard.

⛳️ Requirements

• A minimum of 6 years of experience in offensive security (including red teaming, application security, penetration testing, vulnerability research, etc.).

• At least 1 year of hands-on experience assessing the security of AI/ML systems, with a thorough understanding of vulnerabilities associated with LLMs.

• Strong proficiency in Python for tool development, automation of assessments, and data analysis.

• Demonstrated experience in leading intricate technical projects and/or mentoring security teams, with an outstanding ability to convey critical technical risks to both engineering and executive levels.

🏝️ Benefits

• Time off programs

• Medical

• Dental

• Vision

• Mental health support

• Paid parental leave

• Life and disability insurance

• 401(k)

• Employee stock purchasing program