[Remote] Adversarial AI & Research Engineer

Note: The job is a remote job and is open to candidates in USA. Salesforce is the #1 AI CRM, where humans with agents drive customer success together. The Adversarial AI & Research Engineer will lead adversarial testing and innovate AI attack techniques while building security tooling to enhance the security of AI systems.ResponsibilitiesLead 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 exploitedInnovate 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 artBuild 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 EthicsServe 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 StandardSkills1+ 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 vulnerabilitiesHigh degree of Python proficiency for tool development, assessment automation, and data analysisProven experience leading complex technical projects and/or mentoring security teams, with exceptional ability to communicate high-stakes technical risks to both engineering and executive audiencesAdvanced degree (MS or PhD) in a relevant field, or a public portfolio of security research including conference presentations, published papers, CVEs, or open-source contributionsExperience creating or managing large-scale datasets for security testing or machine learning trainingExperience building automated testing frameworks or large-scale evaluation pipelinesFamiliarity with current AI safety research and frameworks like MITRE ATLAS and the OWASP Top 10 for LLMsBenefitsCertain roles may be eligible for incentive compensation, equity, and benefits.Salesforce offers a variety of benefits to help you live well including: time off programs, medical, dental, vision, mental health support, paid parental leave, life and disability insurance, 401(k), and an employee stock purchasing program.Company OverviewSalesforce is a cloud-based software company that provides customer relationship management software and applications. It was founded in 1999, and is headquartered in San Francisco, California, USA, with a workforce of 10001+ employees. Its website is https://www.salesforce.com.Company H1B SponsorshipSalesforce has a track record of offering H1B sponsorships, with 324 in 2026, 1883 in 2025, 2296 in 2024, 1850 in 2023, 2849 in 2022, 2124 in 2021, 1960 in 2020. Please note that this does not guarantee sponsorship for this specific role.