Adversarial AI & Research Engineer

Salesforce is the #1 AI CRM, where humans with agents drive customer success together. Here, ambition meets action. Tech meets trust. And innovation isn't a buzzword - it's a way of life. The world of work as we know it is changing and we're looking for Trailblazers who are passionate about bettering business and the world through AI, driving innovation, and keeping Salesforce's core values at the heart of it all.

Ready to level-up your career at the company leading workforce transformation in the agentic era? You're in the right place! Agentforce is the future of AI, and you are the future of Salesforce.

The Adversarial AI & Research Team is a specialized group of cross-functional security engineers working at the intersection of offensive security and artificial intelligence. As a strategic partner to Salesforce's AI Research, Ethics, Engineering, and Cybersecurity Operations teams, we mitigate risk across all AI initiatives by developing novel security frameworks, specialized tooling, and foundational testing methodologies for both generative and predictive AI systems.

We are building a robust foundation for AI security through adversarial datasets, in-house content generation systems, and external knowledge sharing - establishing Salesforce as a leader in the AI security field.

• Lead adversarial testing by designing, scoping, and executing red team assessments across our AI ecosystem using a risk-based prioritization approach to discover and address vulnerabilities before they can be exploited.
• Innovate in AI attack techniques by combining cutting‑edge academic research with proven offensive security methods to establish new Tactics, Techniques, and Procedures, and operationalize emerging research to keep assessments aligned with the state of the art.
• Build and scale security tooling using an automation-first philosophy, driving initiatives to shift security testing left by sharing purpose-built tools with AI security stakeholders across Engineering, Research, and Ethics.
• Serve as a strategic partner across the company, providing an offensive security perspective to guide product development, support corporate governance, and contribute to policies such as Salesforce's Generative AI Security Standard.

• 1+ years of experience in offensive security OR adversarial AI testing (red teaming, application security, penetration testing, vulnerability research, etc.).
• 6+ years of direct, hands‑on experience testing the security of AI/ML systems, with a deep understanding of LLM vulnerabilities.
• High degree of Python proficiency for tool development, assessment automation, and data analysis.
• Proven experience leading complex technical projects and/or mentoring security teams, with exceptional ability to communicate high‑stakes technical risks to both engineering and executive audiences.

• Advanced degree (MS or PhD) in a relevant field, or a public portfolio of security research including conference presentations, published papers, CVEs, or open-source contributions.
• Experience creating or managing large-scale datasets for security testing or machine learning training.
• Experience building automated testing frameworks or large-scale evaluation pipelines.
• Familiarity with current AI safety research and frameworks such as MITRE ATLAS and the OWASP Top 10 for LLMs.

If you need a reasonable accommodation during the application or the recruiting process, please submit a request via this Accommodations Request Form.

Please note that Salesforce uses artificial intelligence (AI) tools to help our recruiters assess and evaluate candidates' resumes and qualifications throughout the recruiting process. Humans will always make any candidate selection and hiring decisions. Please see our Candidate Privacy Statement for more information about how we use your personal data and your rights, including with regard to use of AI tools and opt out options.

Salesforce is an equal opportunity employer and maintains a policy of non-discrimination with all employees and applicants for employment. What…