126 to 150 of 232 Red Team Jobs in the UK

Help to shape impactful research proposals during our Research Accelerator Weeks Choose our cohorts for RAW, and help review candidates for MARS Run red‐teaming and proposal development sessions, lab meetings and journal clubs What we’re looking for A strong commitment to acting on the most serious ...

QinetiQ Limited is seeking a Cyber Specialist to join their team in Malvern, England. This full-time position requires expertise in identifying and exploiting security vulnerabilities, developing attack scenarios, and utilizing advanced security techniques. The ideal candidate will possess relevant experience, certifications such as OSCE3 and CCRT ...

techniques. What you’ll be doing Deliver and lead high qualityoffensivesecurity assessments (webapplication,APIand infrastructure), meeting client expectations Get involved in and lead on team assessments asrequired Produce written and verbal reports to clients to an excellent standard. Support the sales team with pre-sales andassistwith technical input … NCSC CHECK TeamLeader(CTL) withat leastPrincipalCyber Security Professional (PriCSP) title- mandatory. Self-motivated and able to work independently and as part of a larger team Produce high-quality technical and executive reports tailored to both technical and non-technical audiences. Holds oris able and willing toobtain a minimum ...

Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. You will write challenging prompts across benign, dual-use, and adversarial levels and judge responses against a defined policy standard. This role requires thorough written rationales and technical writing experience, with emphasis ...

Mercor is assembling a panel of nuclear domain experts in Greater London to red-team frontier AI models. The aim is to test whether a model can correctly judge misuse potential by answering legitimate questions fully while refusing dangerous ones. You will write prompts across benign, dual ...

application. This role also requires full British Nationality at point of application. Note: The above information relates to a specific client requirement As a team: You'll work on innovative projects with colleagues to drive collaboration from strategy through to implementation. You will be using the latest technologies with … help them get to the next level. Do you want to work in an environment where you will be part of a thriving team working on the most complex security challenges in the UK health, public sector, Defence and Central Government. You'll learn, grow and advance ...

design reviews, solution blueprints, threat models, release gates and production readiness; validate controls through testing, abuse-case analysis and red/purple-team exercises. Agent Lifecycle Operations: Own or coordinate secure lifecycle from discovery and registration through build, test, approval, deployment, monitoring, change, suspension and retirement; maintain ...

safety and trustworthiness of AI solutions deployed across the organisation. You will drive modern AI assurance capabilities including automated testing, evaluation frameworks, AI red teaming, observability, reliability engineering and AI safety #J-18808-Ljbffr ...

against persistent threats while integrating safety into the research-to-deployment lifecycle. You will collaborate with software engineers and researchers to push automated red-teaming, threat modeling, and robust defenses in scalable production environments. #J-18808-Ljbffr ...

London and San Francisco is seeking a Security and Controls professional for a full-time role focused on threat modeling, attack design, red-teaming, and product security for an AI agent security product. The position is based in London and SF on-site with options for hybrid arrangements ...

Security Institute in London is seeking a Research Engineer/Scientist for the Control Red Team to advance AI safety through rigorous ML experimentation and adversarial testing. You will design studies, implement attacks, and help quantify how well monitors prevent harm while collaborating with government-facing partners. ...

Mercor is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models. The role involves writing prompts across benign, dual-use, and adversarial levels and evaluating model responses against a policy standard. You will also craft reference answers with technical reasoning. This ...

/ML models, perform edge-case testing on real Android devices, and drive improvements across the development lifecycle. Responsibilities include benchmarking, data curation, red-teaming, automated validation, and producing clear insights for stakeholders. Office visits approx. three times weekly with flexible work arrangements. #J-18808-Ljbffr ...

framework design, including regulated AI decisioning. Experience with ADLC delivery governance and cross-platform AI integration strategy. Skills in frontier-model evaluation and red-teaming, AIOps orchestration architecture and human-agent capability modelling. These will help you succeed Enterprise AI architecture leadership paired with responsible-AI and guardrail ...

team you'll be working with: Role – SENIOR AI SECURITY ARCHITECT ARCHITECT CONSULTANTHybrid Variable - London or BirminghamOverviewWe are seeking an experienced Senior AI Security Architect Consultant to design, implement, and govern secure AI/ML systems across the enterprise. This role is responsible for embedding security, privacy, and trust … grow.what we'll offer you: We offer a range of tailored benefits that support your physical, emotional, and financial wellbeing. Our Learning and Development team ensure that there are continuous growth and development opportunities for our people. We also offer the opportunity to have flexible work options. ...

technical strategy for evaluating models, safety guardrails, and governance across internal platforms, ensuring secure and deterministic AI behavior. You will lead continuous verification, red teaming, and observability initiatives, partnering with AI Foundations and engineering teams to scale safe AI across Kraken’s internal tools. #J-18808-Ljbffr ...

safety across harmful content and risk factors. The Head will partner with model, policy, trust and safety, product, research, and engineering teams, leading red teaming, evaluation frameworks, and client relationships while contributing to business development and governance. #J-18808-Ljbffr ...

Apollo Research · London & San Francisco · Full-time Security and control role supporting threat modeling, attack design, red-teaming, and product security for an AI agent security product. Independent aggregation of a publicly posted role. AI Compliance Index is not affiliated with, endorsed by, or recruiting for Apollo Research. ...

creates real value. You will shape a roadmap grounded in evidence and drive sprint milestones for measurable impact. You’ll establish evaluation rituals, red-teaming and controlled rollouts, while crafting a compelling commercial narrative for buyers. This role demands shipping leadership and expertise in AI-enabled data products. ...

Mercor is assembling a panel of energy and propulsion experts to red-team frontier AI models, testing how well a model judges misuse and safety boundaries. You will write challenging prompts at benign, dual-use, and adversarial levels, evaluate model responses against policy standards, and craft reference ...

Mercor seeks a writer for red-teaming frontier AI models by crafting challenging prompts across benign, dual-use, and adversarial categories. You will evaluate model responses against policy standards and write a reference answer with detailed technical reasoning. This is a writing-intensive role requiring a clear, documented ...

place where everyone can grow, develop and fulfil your potential with meaningful careers. ROLE SUMMARY: This opportunity within the Offensive Security Operations team is a crucial role for the management of vulnerability discovery, offensive testing and remediation activities across the group which protects the business from sophisticated cyber threats … testing, impact and remediation. They will provide insight on root cause analysis and scalable risk management. This role requires working closely within a technical team and with external teams like BISOs, GSOC and regulators. The candidate will stay ahead of emerging cyber security thought leadership and share their ideas ...

place where everyone can grow, develop and fulfil your potential with meaningful careers. ROLE SUMMARY:This opportunity within the Offensive Security Operations team is a crucial role for the management of vulnerability discovery, offensive testing and remediation activities across the group which protects the business from sophisticated cyber threats … testing, impact and remediation. They will provide insight on root cause analysis and scalable risk management. This role requires working closely within a technical team and with external teams like BISOs, GSOC and regulators. The candidate will stay ahead of emerging cyber security thought leadership and share their ideas ...

Life. Job Description Hybrid working - our approach is to be in the office a minimum of 2 days per week. PA’s IT team, internally known as Group Systems, is comprised of a variety of areas that support the wider firm, consisting of four key pillars: Strategy, Architecture … build or run demonstrators that show value concretely is a strong differentiator. Assurance and testing The role should include adversarial testing and red teaming of the organisation's AI systems, whether done directly or by scoping and overseeing third parties. Examples are testing RAG applications for injection ...

Bringing Ingenuity to Life. Hybrid working - our approach is to be in the office a minimum of 2 days per week. PA’s IT team, internally known as Group Systems, is comprised of a variety of areas that support the wider firm, consisting of four key pillars: Strategy, Architecture … build or run demonstrators that show value concretely is a strong differentiator. Assurance and testing The role should include adversarial testing and red teaming of the organisation's AI systems, whether done directly or by scoping and overseeing third parties. Examples are testing RAG applications for injection ...