Adversarial Ai & Research Engineer

Salesforce

Base: $148,500 - $223,900 annually; bonus/equity: ...
6+ years offensive security experience
1+ years ai/ml system testing
Deep understanding of llm vulnerabilities
The role involves leading adversarial testing of AI by designing and executing red team assessments against the company's AI ecosystem

Job Summary

  • The role involves leading adversarial testing of AI by designing and executing red team assessments against the company's AI ecosystem.
  • Candidates will innovate in AI attack techniques by combining academic research with offensive security methods to establish new Tactics, Techniques, and Procedures.
  • Salesforce offers a comprehensive benefits package including time off programs, medical, dental, vision, mental health support, and paid parental leave.

Matching Summary

The role involves leading adversarial testing of AI by designing and executing red team assessments against the company's AI ecosystem.

Salary

Base: $148,500 - $223,900 annually; Bonus/Equity: Not specified; Benefits: Comprehensive package including medical, dental, vision, and 401(k)

Skills & Requirements

Must-have

  • 6+ years offensive security experience
  • 1+ years AI/ML system testing
  • Deep understanding of LLM vulnerabilities
  • High proficiency in Python programming
  • Experience leading complex technical projects

Nice-to-have

  • Advanced degree in relevant field
  • Public portfolio of security research
  • Experience with MITRE ATLAS framework
  • Familiarity with OWASP Top 10 for LLMs
  • Background in automated testing frameworks

Key Requirements

  • 6+ years offensive security experience
  • 1+ years hands-on AI/ML security testing
  • Advanced degree (MS or PhD) preferred
  • Proven leadership in complex technical projects

Work Rights

Not specified

Tailored Resume

Cover Letter