Top Tech Jobs & Startup Jobs in London

The Core Technology Team builds software, infrastructure, evaluation systems, model-hosting platforms, secure access tools, and research applications supporting frontier AI security work. Responsibilities may include contributing to Inspect plugins, supporting open-weight models, scaling secure proxy infrastructure, designing custom research infrastructure, and ensuring robust monitoring and testing for frontier AI evaluations. The opportunity is open to software, research, and security engineers across seniority levels.

The Research Director will lead advanced AI security research focused on frontier AI safety, robustness, and architectures. The role involves shaping research priorities, pursuing high-impact research, collaborating with governments and leading AI companies, publishing externally, and translating technical findings into AI governance and deployment action. The position offers access to frontier models, significant compute, and collaboration across national security, policy, and AI research teams.

Lead the Agentic AI Risk Modelling team’s strategy, research agenda, scientific direction, and delivery. Develop scenario-based analyses of advanced AI risks, identify practical mitigations, and support their adoption by government and industry. Hire, manage, and develop a multidisciplinary team while maintaining rigorous analytical standards and building trusted relationships with senior policy and technical stakeholders across government, academia, and frontier AI companies.

Design and build cyber ranges, CTF challenges, agentic evaluation scaffolding, and infrastructure for testing frontier AI cybersecurity capabilities. Develop metrics, interpret evaluation results, conduct pre-deployment testing, and research novel model behaviors. Collaborate with engineers, researchers, government partners, and AI labs, while communicating findings through reports, papers, and blog posts.

Build and maintain production-quality Python software for AI cybersecurity and autonomy evaluations. Responsibilities include developing cyber-range infrastructure, analysis tooling, sandbox services, image pipelines, and evaluation workflows; leading testing exercises; analysing model behavior; and communicating research findings. The role involves owning technically challenging projects, improving engineering standards, and supporting assessments that inform AI safety standards and government policy.

Research and develop methods for detecting misalignment and loss-of-control risks in frontier AI systems. Build alignment evaluations, conduct pre-deployment testing, analyze model behavior, investigate incidents, and communicate findings to AI companies and governments. The role also involves designing evaluation software and tooling, publishing technical research, threat modeling, and mentoring collaborators. Candidates need substantial AI safety or alignment research experience, strong Python and machine learning engineering skills, and experience with frameworks such as PyTorch or Inspect.

Research Engineer developing AI safety methods focused on human influence. Responsibilities include fine-tuning and post-training LLMs with reinforcement learning, building scalable evaluation and benchmarking pipelines, designing RL environments, applying interpretability techniques, deploying containerized ML systems, and conducting engineering-heavy research on large compute clusters.

Lead and grow the Human Influence engineering function, managing research and software engineers while delivering an engineering roadmap. Design scalable evaluation and benchmarking systems, automated human-AI experiment pipelines, multi-agent study toolkits, data pipelines, reinforcement learning environments, and large-language-model fine-tuning projects. Translate research questions into reproducible production engineering tasks, collaborate with technical and nontechnical stakeholders, and lead projects from scoping through deployment or publication.

Conduct research and engineering on misuse risks in frontier AI systems. Responsibilities include designing and evaluating automated attacks, red-teaming safeguards, developing attack tooling, benchmarking misuse monitoring, investigating data-poisoning attacks and defenses, and producing actionable reports. The role may lead technical research direction or execution, including scalable, reliable, reproducible machine learning experiments and collaboration with frontier AI labs and government stakeholders.

Design and run experiments assessing AI control measures, build adversarial attacks against monitors and sandboxes, and conduct security analyses of frontier AI deployments. Develop reusable ML tooling, automate attack and evaluation loops with LLMs, operate model-training and serving infrastructure, and produce rigorous research and decision-relevant reports for industry and government.