Science - Red Team Engineer

Added 26/08/2026

We are seeking a Science – Red Team Engineer to help evaluate the safety, reliability, and robustness of advanced artificial intelligence systems. In this role, you will design and execute systematic tests that probe model behaviour, identify unexpected capabilities or failure modes, and assess how systems respond to challenging, adversarial, or ambiguous inputs. You will work across research and engineering teams to turn scientific questions into practical evaluation programmes and develop new methods for measuring system performance. Your responsibilities will include creating red-team scenarios, benchmarks, and test suites; conducting structured and exploratory investigations; analysing model outputs and identifying patterns of...

Staff Windows Low Level C++ Engineer - Endpoint security

Added 25/08/2026

We are seeking a Staff Windows Low Level C++ Engineer to help build and evolve advanced endpoint security technologies. You will work at the operating-system boundary, developing reliable, high-performance components that protect devices, applications and data against sophisticated threats. This role is suited to an engineer who combines deep Windows internals knowledge with strong systems programming skills and a passion for solving complex security challenges. Your responsibilities will include designing, implementing and maintaining security-focused Windows components in modern C++, including user-mode and kernel-mode functionality. You will investigate operating-system behaviour, process and memory activity, drivers, services, system calls, access controls and...

Global Security – Red Team Operator - X-Force Red

Added 08/09/2026

We are seeking an experienced Red Team Operator to help assess and strengthen the security of complex environments, applications, infrastructure and connected technologies. In this role, you will plan and execute authorised adversary simulation engagements that replicate realistic cyber threats, identify weaknesses across people, processes and technology, and provide practical recommendations to improve resilience. You will work with clients and internal stakeholders to define objectives, rules of engagement, testing boundaries and success criteria before each engagement. Your responsibilities will include conducting network, web application, cloud, wireless, physical security and social engineering assessments, using both established techniques and creative approaches to...

Principal Engineer - Cybersecurity Science & Analytics

Added 13/10/2026

We are seeking a Principal Engineer – Cybersecurity Science & Analytics to lead the design, development and evolution of advanced security analytics capabilities. This role will apply expertise in cybersecurity, data science, software engineering and threat intelligence to identify emerging risks, improve detection effectiveness and support resilient, intelligence-led security operations. You will work across technical and business teams to translate complex security challenges into scalable solutions that deliver measurable risk reduction. Responsibilities will include defining technical strategy and architecture for cybersecurity analytics platforms; developing statistical, machine learning and rules-based models to detect anomalous activity and sophisticated threats; analysing large, diverse...

Security Engineer (AI Red Team)

Added 07/10/2026

We are seeking a Security Engineer (AI Red Team) to assess the resilience, safety, and security of advanced artificial intelligence systems. In this role, you will plan and conduct adversarial testing across models, applications, agents, and supporting infrastructure. You will investigate weaknesses such as prompt injection, data leakage, insecure tool use, model manipulation, jailbreaks, supply-chain risks, and abuse of integrated APIs. Your work will help identify realistic attack paths and strengthen safeguards before systems are deployed or updated. You will design red-team scenarios, develop automated and manual testing techniques, and evaluate model behaviour under adversarial conditions. Responsibilities include creating test...

Misuse Red Team - Research Engineer/Research Scientist

Added 24/09/2026

We are seeking a Misuse Red Team Research Engineer/Research Scientist to investigate how advanced AI systems may be misused, manipulated, or deployed in harmful ways. You will design and conduct rigorous adversarial evaluations, develop realistic misuse scenarios, and assess model behaviour across areas such as cyber abuse, fraud, privacy, manipulation, disinformation, and other emerging risks. Your work will help identify vulnerabilities before they can be exploited and inform practical improvements to model safeguards, monitoring, and deployment policies. Responsibilities will include creating evaluation methodologies, red-team prompts, automated test suites, and simulation environments; conducting qualitative and quantitative analysis of model outputs; documenting...

Control Red Team - Research Engineer/Research Scientist

Added 24/09/2026

We are seeking a Control Red Team Research Engineer or Research Scientist to investigate how advanced AI systems can be evaluated, challenged and kept reliably under human direction. You will design and conduct rigorous experiments that test model behaviour under adversarial, ambiguous and high-pressure conditions, with a particular focus on control, oversight, robustness and the risk of systems pursuing unintended objectives. Your work will help identify weaknesses in evaluation methods, monitoring approaches and operational safeguards, and translate findings into practical improvements. Responsibilities will include developing threat models and red-team strategies; creating test environments, scenarios and benchmarks; designing automated and human-in-the-loop...

Alignment Red Team - Research Engineer/Research Scientist

Added 16/09/2026

We are seeking an Alignment Red Team Research Engineer/Research Scientist to investigate how advanced AI systems can fail, be misused, or behave unexpectedly under challenging conditions. You will design and conduct rigorous adversarial evaluations of models, agents, and safety mechanisms, with the goal of identifying vulnerabilities before they create meaningful real-world risks. The role combines scientific research, engineering, critical thinking, and practical experimentation in a highly collaborative environment. Your responsibilities will include developing threat models and evaluation methodologies; creating adversarial prompts, scenarios, tools, and test environments; probing models for deceptive, unsafe, biased, or otherwise misaligned behaviour; and building automated pipelines...

Control Red Team - Research Engineer/Research Scientist

Added 04/09/2026

We are seeking a Control Red Team Research Engineer/Research Scientist to investigate how advanced technical systems behave under challenging, adversarial, and unexpected conditions. In this role, you will design and execute red-team evaluations that identify weaknesses in system control, reliability, alignment, safety, and robustness. You will work across research and engineering disciplines to develop realistic threat models, construct rigorous test environments, and translate experimental findings into practical improvements. Your responsibilities will include developing novel evaluation methodologies, automated testing tools, and experimental protocols; creating challenging scenarios and datasets; analysing system behaviour using quantitative and qualitative techniques; and documenting vulnerabilities, failure modes,...

Misuse Red Team - Research Engineer/Research Scientist

Added 04/09/2026

We are seeking a Misuse Red Team Research Engineer/Research Scientist to investigate how advanced AI systems could be misused, deliberately or unintentionally, and to develop rigorous methods for identifying, measuring, and reducing associated risks. You will design and conduct adversarial evaluations across a range of capabilities and deployment contexts, examining how systems respond to challenging requests, ambiguous instructions, social engineering, prompt manipulation, and attempts to bypass safeguards. Your work will help improve the reliability, robustness, and responsible use of AI technologies. Responsibilities include developing red-team methodologies, evaluation datasets, and automated testing tools; carrying out structured and exploratory assessments; analysing model...

Misuse Red Team - Research Engineer/Research Scientist

Added 03/09/2026

We are seeking a Misuse Red Team Research Engineer/Research Scientist to investigate how advanced AI systems may be misused, manipulated, or adapted for harmful purposes. You will design and execute rigorous adversarial evaluations across a range of capabilities, including persuasion, cyber misuse, privacy, fraud, biological or chemical risk, and other emerging threat areas. Your work will help identify weaknesses before they can be exploited and inform practical improvements to model behaviour, safeguards, monitoring, and deployment decisions. You will develop threat models, misuse scenarios, test plans, and evaluation methodologies; conduct experiments using language models, tools, agents, and multimodal systems; and analyse...

Control Red Team - Research Engineer/Research Scientist

Added 03/09/2026

We are seeking a Control Red Team Research Engineer or Research Scientist to investigate how advanced AI systems can be evaluated, monitored, and controlled under challenging or adversarial conditions. You will design and conduct research that probes model capabilities, identifies weaknesses in safeguards, and tests whether systems behave reliably when exposed to unexpected inputs, strategic pressure, or attempts to circumvent established controls. Your work will help inform practical approaches to robust deployment, oversight, and risk reduction. Responsibilities will include developing red-team methodologies, constructing evaluation environments, and creating challenging test cases across areas such as deceptive behaviour, instruction following, tool use,...

Executive Principal Consultant - Red Team

Added 02/10/2026

We are seeking an Executive Principal Consultant – Red Team to lead high-impact cyber security engagements that assess and strengthen the resilience of complex organisations. In this senior role, you will provide strategic direction across red teaming, adversary simulation, penetration testing and threat-informed defence activities. You will work with senior stakeholders to identify critical risks, challenge existing assumptions and translate technical findings into clear, actionable business recommendations. Your responsibilities will include shaping engagement strategies, defining scopes and objectives, leading complex assessments, and ensuring delivery to a consistently high standard. You will oversee multidisciplinary teams conducting realistic attacks across infrastructure, cloud...

Executive Principal Consultant - Red Team

Added 02/10/2026

We are seeking an Executive Principal Consultant – Red Team to lead complex cybersecurity assessments and advise senior stakeholders on organisational resilience. This is a senior-level opportunity for an accomplished security professional who can combine technical depth, strategic thinking and strong client engagement skills. You will be responsible for shaping and delivering sophisticated red team engagements that test people, processes, technology and physical controls across a range of environments. Your responsibilities will include defining engagement objectives and rules of engagement, developing realistic attack scenarios, leading end-to-end operations and coordinating multidisciplinary teams. You will oversee reconnaissance, threat emulation, social engineering, physical...