Senior Security Engineer

Senior AI Security EngineerLondon HybridThe client:This company uses AI to change how new medicines are discovered. Their platform runs on autonomous AI agents, right at the edge of what's currently possible, and they need security to keep pace with that speed.Reporting straight into the CISO. Think of yourself as the bridge between ML engineering, platform architecture, and security, making sure nothing sensitive gets exposed as the science moves fast.Its still a scaling environment. Theres ambiguity, and youll be expected to take ownership and shape how security is designed and implemented across the business.The role:As Senior AI Security Engineer, you'll take ownership of security across the AI platform and its agentic systems.Map out the threats specific to AI and ML, and build that into a proper risk frameworkDecide how model weights, training data, and code get tracked and locked downBuild guardrails and sandboxing for LLMs and autonomous agents, with real-time monitoring behind itWork closely with ML researchers and engineers, embedding security across the whole ML lifecycleLead the response when something goes wrong, using ML techniques to catch what standard tools missHelp turn emerging AI regulation into something the business can actually keep up withPartner with Legal and Compliance to shape what responsible AI security looks like in practiceAbout you (skills/experience):You will bringA genuine understanding of deep learning (JAX, PyTorch, or TensorFlow), and you've worked with large-scale cloud training or inference infrastructureThink like an attacker on AI systems: prompt injection, model inversion, and data poisoning are all familiar, and you know the OWASP Top 10 for LLMs and MITRE ATLASProven experience in securing agentic systems before, and understand identity and access controls between agentsComfortable in cloud security, GCP ideally, with solid container and multi-cloud experienceCan write production-grade code, Python preferred, so you build your own toolingCommunicate well, sit comfortably with ambiguity, and can turn ML risk into something engineers can act onNice to have:Red-teaming LLMs, agent networks, or ML backendsBackground in BioTech, Pharma, or Deep TechDegree in Computer Science, Machine Learning, Cybersecurity, or similarOSCP or a cloud security certificationWhat they can offer:Market-leading compensation (bonus + equity)Hybrid working (3 days in a central London office)If owning the security for the world's leading AI drug discovery company sounds of interest, apply now or drop me a message if you want to talk it through.Keywords: AI Safety, AI Security, LLM Security, Agentic Security, Prompt Injection, Adversarial ML, MITRE ATLAS, GCP, Cloud Security, Python, Model Risk, Machine Learning, CybersecurityTPBN1_UKTJ