2 of 2 Contract Red Team Jobs in London

Duration of assignment - 1 Year with likely extension Standard Working hours. Key responsibilities : AI Security Engineerings LLM Security/Model Security experts AI Red Teaming … specialists AI Governance & Guardrails specialists Security Data Scientists Secure CI/CD pipelines Secure configuration management Person specification: I.e., negotiating, client facing, communication, assertive, team leading/team member skills, supportive : Excellent stakeholder management and client-facing skills with the ability to build strong professional relationships. Strong team ...

secrets management and API key protection . Address risks associated with data leakage, credential exposure and secret exfiltration . Implement AI evaluation frameworks, red-teaming approaches and appropriate guardrails . Establish safeguarding controls where AI-enabled services may interact with younger or potentially vulnerable users . Introduce monitoring … . Experience implementing AI-enabled engineering workflows . Strong understanding of large language models and agentic architectures . Experience with LLM evaluation, testing, red-teaming and guardrail design . Strong understanding of AI security risks and appropriate mitigation strategies . Experience introducing engineering standards, governance or organisational controls ...