Senior Director of Engineering - Penetration Testing & AI Exploitation

About Salesforce

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.

About The Role: Senior Director of Engineering - Penetration Testing & AI Exploitation

We are seeking a Senior Director of Penetration Testing & AI Exploitation to lead and scale a focused offensive security function dedicated to deep technical penetration testing and advanced AI/ML exploitation across our products and platforms. This role owns the strategy, execution, and evolution of manual, research-driven penetration testing and AI-specific attack discovery, ensuring high-risk vulnerabilities are identified early, validated rigorously, and translated into clear, actionable remediation guidance for engineering teams. The mandate is depth over breadth: fewer assessments, higher quality findings, and meaningful reduction of systemic risk—especially in AI-powered and data-driven systems.

Key Responsibilities

• Penetration Testing Leadership
  • Own and execute the global penetration testing strategy across applications, APIs, cloud services, and shared platforms.
  • Drive deep, manual, and white-box testing for high-risk products, features, and architectural changes.
  • Ensure penetration testing goes beyond checklists, focusing on real exploitability and impact.
  • Establish standardized scoping, rules of engagement, reporting quality, and validation practices.
• AI Exploitation & Security Research
  • Lead AI/ML exploitation efforts, focusing on vulnerabilities in:
  • LLM-powered features and agents
  • Prompt injection, indirect prompt abuse, and tool misuse
  • Model data leakage, training data exposure, and inference-time attacks
  • Authorization, trust-boundary, and privilege escalation flaws in AI workflows
  • Drive original offensive research into emerging AI attack techniques and publish internal research artifacts to guide engineering defenses.
  • Partner with AI platform and product teams to influence secure-by-design patterns for AI systems.
• Program Execution & Quality
  • Ensure all findings are:
  • Reproducible and technically validated
  • Clearly prioritized by risk and exploitability
  • Accompanied by precise remediation guidance, including short- and long-term fixes for systemic issues
  • Track remediation progress and validate fixes for high-risk findings.
• Organizational Leadership
  • Build and lead a high-caliber team of senior penetration testers and AI security researchers.
  • Define role expectations, technical bars, and career progression for pentest and AI exploitation specialists.
  • Own hiring strategy, vendor augmentation (where appropriate), and budget for the function.
• Cross-Functional Partnership
  • Partner closely with:
  • Product Security and Engineering teams during design, pre-GA, and major architectural shifts
  • Platform and AI infrastructure teams to assess shared services and foundational components
  • Provide expert guidance to leadership on pentest risk, AI exploitation trends, and systemic exposure.

Required Qualifications

• 12+ years of experience in penetration testing, offensive security, or vulnerability research, including leadership of senior technical teams.
• Deep hands-on expertise in:
• Application, API, cloud, and platform security
• Advanced exploit chains and logic flaws
• Demonstrated experience testing or attacking AI/ML systems, LLM-based features, or data pipelines.
• Strong ability to translate complex technical findings into clear engineering actions and leadership narratives.

Preferred Qualifications

• Background in vulnerability discovery or offensive security research.
• Experience assessing AI agents, autonomous workflows, or model-integrated products.
• Experience integrating automation or AI-assisted techniques into penetration testing workflows.
• Security research publications, talks, or tooling contributions (internal or external).

Key skills/competency

• Penetration Testing
• AI Exploitation
• Offensive Security
• Vulnerability Research
• Security Leadership
• AI/ML Security
• Cloud Security
• API Security
• Prompt Injection
• Exploit Development