AVP, Penetration Tester (LLM)

LPL Financial•Fort Mill, SC

5d•$128,647 - $214,343•Hybrid

About The Position

As a member of the Cyber Security team, an AVP Penetration Tester of Offensive Security will be responsible for helping with the scheduling, scoping, and execution of internal penetration testing with a strong focus on Large Language Model (LLM), agentic built applications, and supporting API penetration testing. This role will perform, at advanced levels, manual penetration testing to validate the security of resources across the company as assigned. Candidates will perform hands-on testing as well as serve as the point of contact for the assigned penetration testing activities as a part of their regular duties. The ideal candidate must possess a highly technical skill set, the ability to collaborate with stakeholders across the company to help recommend, as well as test mitigation strategies for challenging, systemic issues, across LPL applications. Offensive Security is a top area of focus at LPL. This is an exciting time to join the Information Security team as we look for highly skilled people to help expand the current program.

Requirements

5+ years’ experience conducting application/API and network-based penetration-testing engagements.
5+ year’ troubleshooting tools, manually finding issues in code, and rewriting code to remove bugs.
3+ years’ experience leading penetration testing engagements end-to-end.
2+ years' experience pentesting AI/LLM/GenAI applications
2+ years' experience using AI Models such as Claude to rapidly develop tooling.
Advanced level of knowledge with security assessment tools and frameworks, including Burp Suite, Promptfoo, HexStrike, Claude, CAI, Garak, Pyrit, Kali Linux, Nessus, Metasploit, Cobalt Strike, Mitre Atlas, OWASP Top 10 for LLM, and similar.
At least one industry certification such as OSCP, OSAI, OSCE, OSWE, GPEN, GCIH, GWAPT, or GXPN.
Excellent communication skills and ability to collaborate with all stakeholders, internal and external, finding, advising, and implementing the best solutions.
Strong organizational skills
Insatiable curiosity for tinkering with and circumventing security features and controls.

Nice To Haves

Bachelor’s Degree or equivalent in Information Security, Engineering, or Computer Science.
Advanced understanding of OWASP, the MITRE ATT&CK framework, Atlas, and the software development lifecycle (SDLC).
Advanced knowledge and experience penetration testing AI/LLM systems including MCP servers, Models, and Chatbots.
Advanced understanding of tool development with the use of AI such as Claude Code.
Advanced knowledge in programming languages (.NET, JavaScript, Python, Java, PowerShell, Perl, Ruby, Bash, C#, Golang, or similar).
Advanced level knowledge of Linux/Mac/Windows operating systems, AWS/Azure cloud environments, and cloud-native resources (ex. Containers, Kubernetes, microservices, serverless functions)
Breadth and depth of knowledge in security of LLM systems such as MCP servers, models, tooling, and infrastructures.

Responsibilities

Partner with product stakeholders to drive end-to-end pentesting activities. Including working with Security Architects during the SDLC processes for LLM / AI to make recommendations and offer our ability to identify security weaknesses in applications prior to production deployment.
Conduct tactical security penetration test assessments to validate the security of company applications (LLM, agentic built applications, and supporting APIs) against OWASP Top 10 threats work with the Application Security team to provide feedback, and recommendations to increase automated capabilities to include ai assisted tooling.
Think creatively and strategically to circumvent security guardrails, identify vulnerabilities, and develop effective mitigation strategies for ai.
Stay informed on ever-emerging and fast-changing TTPs, zero-days and remediation strategies for Agentic developed applications, systems, and their supporting infrastructure.
Develop/modify custom tooling to solve new needs with the use of models such as Claude.
Document and formally report testing initiatives, test findings, justified risk ratings, remediation recommendations, and validation results in a clear and concise manner.
Partnering with technology teams to present security testing results, highlight the threat presented, and consult on remediation guidance in a way that is easy IT stakeholders to understand.
Perform assessments of internal/external networks, infrastructure, cloud environments, along with a wide array of internally developed and commercial products.
Help develop and maintain tools or scripts used in agentic penetration testing.
Lead the execution of assigned Ai/LLM penetration testing initiatives to communicate status to leadership.
Oversee communication and reporting of findings identified during testing activities and performing retesting to validate successful closure of previously identified findings.
Develop tooling for agentic assisted LLM pentesting.