Senior Penetration Testing Engineer

Overview

The Business Security Assurance Pentest Team tests Microsoft products and services in regulated industries, including commerce, healthcare, finance, HR and legal. More and more of these products are built on generative AI, AI agents, and Model Context Protocol (MCP) integrations. As a Senior Penetration Testing Engineer , you'll find vulnerabilities across traditional systems and AI systems and help scale how we test them.

Join us in this exciting opportunity to collaborate with some of the brightest minds in the industry and help shape the future of cybersecurity at Microsoft. Your intelligence, creativity, and dedication will be key to elevating our organization's security standards.

Microsoft's mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

In alignment with our Microsoft values, we are committed to cultivating an inclusive work environment for all employees to positively impact our culture every day.

Responsibilities

• Plan, research and run manual penetration tests that simulate real-world attackers against Microsoft services, cloud infrastructure, identity, APIs and applications in regulated industries.

• Test LLM-powered and agent-based applications for prompt injection (direct and indirect), jailbreaks, system-prompt and sensitive-data leakage, insecure output handling, misuse of tool and function calls, excessive agent permissions, and abuse of agent memory and context.

• Assess the security of agents and MCP servers: tool permissions, authentication and authorization between agents and tools, trust boundaries between agents, and how far an attacker can get when an agent is compromised.

• Assess the AI supply chain and data pipelines, including retrieval (RAG) data sources, vector stores, model and plugin provenance, and the risk of poisoned training or fine-tuning data.

• Chain findings across application, cloud, identity, and network layers into realistic attack paths that show business and customer impact.

• Clarify priorities and dependencies across groups, explain key security issues to upper management, and work with partners to put fixes in place.

• Use AI agents to speed up recon, triage and regression testing, with clear guardrails and human sign-off.

• Keep up with new attack research and turn it into team guidance, training and awareness across the Microsoft Security community.

Qualifications

Required Qualifications:

• Master's Degree in Statistics, Mathematics, Computer Science, or related field AND 3+ years experience in security or related field

• OR Bachelor's Degree in Statistics, Mathematics, Computer Science, or related field AND 4+ years experience in security or related field

• OR equivalent experience.

Other Requirements:

Candidates must be able to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include, but are not limited to the following specialized security screenings:

• Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud background check upon hire/transfer and every two years thereafter.

Preferred Qualifications:

• 5+ years of hands-on penetration testing or red teaming across cloud (Azure, AWS, GCP), web and API, identity, and network.

• Hands-on experience assessing LLM applications or AI agents in production or pre-production, using the OWASP LLM Top 10, OWASP Agentic AI guidance and MITRE ATLAS.

• Understanding modern AI architectures: retrieval-augmented generation (RAG), agent orchestration frameworks, function and tool calling, MCP, and cloud AI platforms such as Azure AI Foundry, Azure OpenAI, Amazon Bedrock or Vertex AI.

• Strong coding in Python plus one or more of C#, Go, PowerShell, JavaScript/TypeScript or Rust. Able to turn research into tools you can run in engagements.

• Experience with tools such as Burp Suite Pro, Metasploit, Cobalt Strike or Sliver, AI tooling etc .

• Familiarity with governance and regulatory frameworks relevant to regulated industries: NIST AI RMF, EU AI Act, ISO 27K, HIPAA, PCI-DSS, SOC2 etc.

• Experience with APT emulation, purple teaming, threat intelligence, or bypassing operating systems and security control mitigations, including AI guardrails and content filters.

• Certifications such as OSCP, OSEP, GPEN, GWAPT or GXPN, and AI-security credentials.

• Strong teamwork, comfort with ambiguity, and the ability to mentor peers and learn new attack techniques quickly.

Penetration Testing IC4 - The typical base pay range for this role across the U.S. is USD $119,800 - $234,700 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $160,200 - $261,000 per year.

Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here:

This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.

Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations. (