Red Team Engineer – AI & Offensive Security 80 - 100% (f/m/d) Zurich • Bendern

LGT is the largest Private Banking and Asset Management group in the world to be owned by an entrepreneurial family. As the family office of the Princely House of Liechtenstein, we have years of experience in the management of sizeable sums of assets.

We are looking for a Red Team Engineer to help further develop our red teaming capabilities and to run realistic, adversary-focused tests across our applications, cloud services, infrastructure and workplace environments. This role combines hands-on offensive security with the chance to help shape and mature our red teaming programme, and it makes heavy use of AI — both to develop AI-assisted penetration testing and to test the security of our own internal AI platforms.
You will work with architects, engineers, developers, blue team, risk functions and business teams to turn offensive findings into practical improvements that make our defences stronger in real life — not just on paper.

Key Responsibilities

• Help mature and expand our red teaming capabilities, contributing to methodology, rules of engagement, tooling and reporting
• Plan and execute penetration tests and red team engagements against applications, cloud services, infrastructure and critical systems
• Develop and apply AI-assisted penetration testing — using AI to accelerate reconnaissance, exploitation, payload generation and reporting across the engagement lifecycle
• Test the security of our internal AI platforms, including prompt injection, model abuse, data exfiltration and other AI-specific attack techniques
• Work with the blue team to optimise detection and response, feeding real attack scenarios we were able to exploit into new detections; run adversary emulation and purple team exercises to validate detection and response capabilities
• Document findings clearly, prioritise by risk and drive remediation with the affected teams; contribute to security standards, KPIs and reporting
• Support incident handling and root-cause analysis where offensive security expertise adds value
• Work closely with infrastructure, development, operations, governance and risk teams to embed offensive testing into the wider security lifecycle

• Several years of hands-on experience in penetration testing, red teaming or offensive security
• Proven penetration testing skills across at least two areas such as web and application testing, network and infrastructure, cloud (Azure / M365), AI, Active Directory / identity, or social engineering
• Practical experience with offensive tooling and frameworks such as Metasploit, Burp Suite or comparable, and familiarity with MITRE ATT&CK
• Experience with scripting and exploit development, for example Python, PowerShell, Golang or similar
• Solid understanding of how to use AI in offensive security and awareness of AI-specific attack surfaces (e.g. prompt injection, model and data abuse); knowledge of common frameworks such as OWASP, MITRE ATT&CK or NIST
• Structured, reliable and solution-oriented way of working
• Strong communication skills and the ability to make technical findings understandable and actionable for technical and non-technical audiences
• Very good English skills; German is an advantage
• Willingness to participate in 24/7 on-call duty

Nice to Have

• Experience in regulated environments or financial services
• Offensive security certifications such as OSCP, OSEP, CRTO, CRTP or GPEN​

Please note that applications submitted via recruitment agencies cannot be considered for this position.