Description
We are seeking a Red Team Lead, AVP to join our AI Security Team at DWS Group in Madrid.
As a Red Team Lead, AVP, you will be responsible for leading adversarial testing of AI platforms and applications to identify exploitable weaknesses, validate security controls, and strengthen the Company's resilience against emerging AI-driven threats.
Your responsibilities include:
- Developing the firm's AI red-team methodology and testing standards
- Testing for prompt injection, jailbreaks, data exfiltration, RAG manipulation, and agent/tool abuse
- Conducting adversarial testing of material AI use cases before production
- Providing risk-rated findings and actionable remediation guidance
- Tracking emerging AI attack techniques and incorporating them into testing
To be successful in this role, you will need:
- 8+ years of offensive security, penetration testing, application security, or vulnerability research experience, with recent hands-on testing of AI/ML, LLM, RAG, or agentic systems
- Strong experience discovering, validating, risk-rating, and communicating vulnerabilities across applications, APIs, cloud platforms, identity, and data flows
- Ability to extend established offensive-security techniques to frontier AI threats including prompt injection, jailbreaks, data exfiltration, RAG manipulation, agent/tool abuse, and AI supply-chain attack paths
- Experience partnering with engineering teams through remediation, retesting, and closure
- Proven ability to leverage AI tools to enhance productivity, optimise workflows to solve business problems, while applying critical judgment to ensure responsible and ethical use of data and AI outputs
At DWS, we're serious about diversity, equity and creating an inclusive culture where colleagues can be themselves and it's important to us that you enjoy coming to work - feeling healthy, happy and rewarded.
We offer a range of benefits, a hybrid working model, and a culture that values diversity, equity, and inclusion.