Senior Offensive Security Consultant (AI Red Teaming)

About Stone Cybersecurity Stone Cybersecurity is a CREST-accredited cybersecurity company and a Cyber Security Agency (CSA) licensed provider, delivering advanced cybersecurity services across Offensive Security, AI Security, Governance, Risk & Compliance (GRC), and Managed Security Services. Our consultants work with organisations across government, healthcare, financial services, critical infrastructure, manufacturing, education, and multinational enterprises to strengthen their cyber resilience through cutting-edge security assessments and advisory services. Our service offerings include: AI Red Teaming Red Teaming & Adversary Simulation Vulnerability Assessment & Penetration Testing (Web, Mobile, API, Network, Cloud, OT & IoT) Secure Source Code Review Security Architecture Review Threat Modelling AI Security Assessments ISO/IEC 27001 Consulting & Internal Audits Cyber Essentials Mark (CEM) Cyber Trust Mark (CTM) Data Protection Trustmark (DPTM) Virtual CISO (vCISO) Managed Detection & Response (MDR) Security Operations Centre (SOC) Security Awareness Training & Phishing Simulation About the Role We are looking for a highly skilled, strategic, and detail-oriented Senior Offensive Security Consultant (AI Red Teaming) to join our growing Offensive Security team. If you’re passionate about offensive security, enjoy thinking like an adversary, and want to help organisations secure next-generation AI systems alongside traditional enterprise environments, we’d love to hear from you. In this role, you will lead and execute advanced AI Red Teaming engagements, penetration testing, secure source code reviews, and offensive security assessments across AI applications, cloud environments, enterprise infrastructure, web applications, APIs, mobile applications, and networks. You will work directly with clients to identify security weaknesses, demonstrate real-world attack scenarios, and deliver practical remediation recommendations that strengthen their overall cybersecurity posture. Key Responsibilities AI Red Teaming Lead and execute end-to-end AI Red Teaming engagements against Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) systems, AI Agents, and AI-powered applications. Conduct comprehensive multi-stage adversarial assessments including:ReconnaissancePrompt InjectionIndirect Prompt InjectionJailbreak TestingTool AbuseData ExfiltrationModel ManipulationPrivilege EscalationBusiness Logic Abuse Assess AI systems for:Prompt LeakageSensitive Data LeakageExcessive AgencyInsecure Output HandlingAI Supply Chain RisksUnsafe Tool UsageInsecure Integrations Offensive Security Conduct Web Application Penetration Testing. Perform API Security Assessments. Conduct Mobile Application Penetration Testing (Android & iOS). Perform Thick Client Application Security Assessments. Conduct Internal and External Network Penetration Testing. Conduct Active Directory security assessments and privilege escalation testing. Perform secure source code reviews across modern programming languages. Execute Red Team exercises where required. Client Engagement Produce high-quality technical reports with clear, actionable remediation recommendations. Present findings to technical teams, management, and executive stakeholders. Support remediation validation and retesting activities. Provide security advisory throughout client engagements. Research & Innovation Stay current with emerging AI attack techniques, offensive security research, and cybersecurity trends. Contribute to internal methodologies, tooling, automation, and knowledge sharing. Assist in developing new AI Security and Offensive Security service offerings. Requirements Experience Minimum 3 years of hands-on experience in offensive security or penetration testing. Demonstrated experience conducting and leading enterprise AI Red Teaming engagements. Proven experience leading multi-stage offensive security assessments from reconnaissance through impact validation. Hands-on experience performing secure source code reviews. Experience conducting Web, API, Mobile, Thick Client, Infrastructure, Cloud, and Network Penetration Testing. Technical Knowledge Strong understanding of: OWASP Web Security Testing Guide (WSTG) OWASP ASVS OWASP API Security Top 10 OWASP Top 10 for LLM Applications MITRE ATT&CK Framework Hands-on experience with: Prompt Injection Indirect Prompt Injection Jailbreaking RAG Security AI Agent Security Tool Abuse Model Manipulation Sensitive Data Leakage AI Su…