Staff Engineer - Offensive Security

Twilio Twilio · Enterprise · United States · Remote · Business Operations

Staff Engineer focused on Offensive Security, specifically performing penetration testing, network audits, and adversary emulation. This role involves AI/LLM probing, building automated testing frameworks for AI systems, and developing custom exploits. Requires expertise in offensive security tools, scripting, and understanding of AI security concepts like prompt injection and adversarial ML.

What you'd actually do

  1. AI/LLM Probing: Perform initial prompt injection and jailbreak tests on AI prototypes, services, and applications using established checklists (OWASP Top 10 for LLMs).
  2. AI Red Teaming Architecture: Build automated testing frameworks for AI systems (e.g., using PyRIT, Promptfoo, or Garak) to test for models related to sensitive data leakage.
  3. Custom Exploit Development: Build custom payloads, droppers, and obfuscated scripts to bypass EDR/AV and maintain stealth.
  4. Full-Stack Penetration Testing: Perform manual and automated testing of web applications, APIs, and mobile apps (iOS/Android).
  5. Adversary Emulation: Design and lead multi-week Red Team operations that mimic specific threat actors (APTs) to test the SIRT detection capabilities.

Skills

Required

  • 7-10 years in offensive security, penetration testing, a high-volume bug bounty background, AppSec, or vulnerability exploitation
  • Expert Knowledge and solid understanding of the MITRE ATT&CK matrix and the OWASP Top 10 for web applications and top 10 for LLMs, post exploitation (lateral movement, persistence, data exfiltration) and Adversarial ML
  • Proficient in OffSec popular tools like Burp Suite professional, Nmap, Metasploit, Wireshark etc... and AI security tools such as LangChain, TensorFlow for adversarial testing or, as well as use of C2 frameworks (Cobalt Strike, Sliver, Havoc) or similar tools
  • Ability to write functional scripts in Python or Bash to automate repetitive testing tasks and proficiency in coding and scripting like Python, C++, and scripting for creating custom offensive exploits that avoids signature-based detection.

Nice to have

  • OSCP, OSEP, OSWE, GXPN or similar training in OffSec tracks
  • Telecom expertise

What the JD emphasized

  • track record of finding high/critical vulnerabilities in complex environments
  • Expert Knowledge and solid understanding of the MITRE ATT&CK matrix and the OWASP Top 10 for web applications and top 10 for LLMs
  • Adversarial ML

Other signals

  • AI Red Teaming Architecture
  • AI/LLM Probing
  • Adversarial ML