Назад
Company hidden
9 дней назад

AVP, Penetration Tester (LLM)

128 647 - 214 343$
Формат работы
hybrid
Тип работы
fulltime
Грейд
senior/lead
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
AVP, Penetration Tester (LLM) (LLM/AI offensive security): Leading internal penetration testing for LLM, agentic applications, APIs, networks, infrastructure, and cloud environments with an accent on manual vulnerability discovery, security guardrail bypasses, and custom AI-assisted tooling. Focus on developing Claude-based testing tools, validating OWASP risks, directing end-to-end engagements, and communicating remediation findings to technical stakeholders and leadership.

Location: Austin, TX; hybrid work arrangement. Valid U.S. work authorization without employer sponsorship is required.

Salary: $128,647–$214,343 base salary annually.

Company

hirify.global is a U.S. wealth management and financial technology firm supporting financial advisors and institutions with investment solutions, advisor affiliation models, and technology resources.

What you will do

  • Schedule, scope, lead, and execute internal penetration testing engagements for LLM, agentic applications, APIs, networks, infrastructure, cloud environments, and commercial products.
  • Identify vulnerabilities and circumvent security guardrails across AI systems, MCP servers, models, chatbots, and supporting infrastructure.
  • Partner with product stakeholders and Security Architects throughout the SDLC to assess risks before production deployment.
  • Develop and maintain custom tooling and scripts for AI-assisted and agentic penetration testing, including tools built with models such as Claude.
  • Document findings, risk ratings, remediation recommendations, and validation results; perform retesting to confirm issue closure.
  • Present testing results to technology teams and leadership and advise on practical mitigation strategies.

Requirements

  • 5+ years of application, API, and network penetration-testing experience.
  • 3+ years leading penetration-testing engagements end to end.
  • 2+ years of penetration testing AI, LLM, or GenAI applications.
  • 2+ years using AI models such as Claude to rapidly develop tooling.
  • Advanced knowledge of security assessment tools and frameworks, including Burp Suite, Promptfoo, HexStrike, Garak, Pyrit, Kali Linux, Nessus, Metasploit, Cobalt Strike, MITRE ATLAS, and OWASP Top 10 for LLM.
  • At least one relevant certification, such as OSCP, OSAI, OSCE, OSWE, GPEN, GCIH, GWAPT, or GXPN, plus strong communication and organizational skills.

Nice to have

  • Bachelor’s degree or equivalent in Information Security, Engineering, or Computer Science.
  • Experience with MCP servers, LLM models, chatbots, and AI-assisted tool development.
  • Programming experience with .NET, JavaScript, Python, Java, PowerShell, Perl, Ruby, Bash, C#, or Golang.
  • Knowledge of Linux, macOS, Windows, AWS, Azure, containers, Kubernetes, microservices, and serverless functions.

Culture & Benefits

  • Collaborative, team-oriented environment focused on innovation, continuous improvement, and integrity.
  • Opportunity to expand the offensive security program and work on emerging AI security challenges.
  • 401(k) matching, health benefits, employee stock options, paid time off, and volunteer time off.
  • Resources and autonomy to make an impact while supporting financial advisors and their clients.

Hiring process

  • LPL communicates with applicants directly from an @lplfinancial.com email address.
  • Interviews are not conducted online through chatroom forums, and applicants will not be asked for payment or bank and credit card information.

Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →