← All roles

Senior Security Engineer (AI Safety), London, Lausanne

Isomorphic Labs· Tech
Apply on company site
Hybrid (London/Lausanne)Full-timePosted 3mo ago

About the role

Senior AI Security Engineer focused on securing an AI-first drug discovery platform at Isomorphic Labs. Reports to the CISO and works at the intersection of AI/ML engineering, platform security, and adversarial defense to protect models, data, and workflows in a hybrid London/Lausanne setting.

Responsibilities

  • Adversarial Threat Modeling: Conduct cutting-edge threat modeling focused on AI/ML vulnerabilities, engineering a comprehensive risk management framework tailored to an AI-powered life sciences platform.
  • Model Artifacts Protection: Partner with AI teams to establish a granular inventory, classification and protection framework for ML models’ weights, code, and training data.
  • Agentic AI & LLM Guardrails: Design and deploy scalable guardrails, robust sandboxing, and real-time monitoring controls for our extensive LLM ecosystem, including ADK, MCP, and autonomous agentic workflows.
  • Collaborative Security Engineering: Partner with ML researchers and platform engineers to design and implement robust security controls across the entire ML lifecycle—from data ingestion and training pipeline integrity to inference runtime controls.
  • Model-Driven Incident Response: Act as the primary technical expert for AI security incidents, deploying advanced machine learning techniques to automate threat hunting, anomaly detection, and signatureless mitigation specific to LLMs.
  • Compliance & Governance Automation: Bridge the gap between complex AI architectures and emerging global regulations (e.g., EU AI Act) by automating risk posture monitoring and continuous compliance metrics.
  • AI Safety Frameworks: Pioneer the practical implementation of Isomorphic Labs' AI Safety standards, working in close coordination with Legal, Compliance, and external partners like Google DeepMind.

Qualifications

  • AI/ML Engineering: Deep conceptual and practical understanding of deep learning frameworks (e.g., JAX, PyTorch, TensorFlow), large-scale cloud training or inference infrastructure, and LLM ecosystems.
  • Adversarial ML Mindset: Strong familiarity with AI security threat vectors (prompt injection, model inversion, data poisoning) and frameworks like OWASP Top 10 for LLMs or MITRE ATLAS.
  • Agentic Frameworks Security: Proven experience securing agentic frameworks (ADK, MCP), agentic first infrastructure and implementing robust agent-to-agent (A2A) identity and access controls.
  • Infrastructure Security: Solid proficiency in cloud platform security (GCP preferred), including container security, multi-cloud/SaaS integrations, and strict network isolation boundaries.
  • Pragmatic Risk Assessment: Proven ability to define and execute pragmatic mitigation strategies that balance a rigorous security posture with the high-velocity needs of a world-class scientific research organization.
  • Software Development & Automation: Ability to write production-grade code (Python preferred) to build custom security tooling, automate telemetry collection, or enforce policy layers.
  • Translational Communication: Exceptional skills in navigating ambiguity, building trusted relationships with AI researchers, and clearly translating complex machine learning risks into actionable engineering tasks for leadership.

Skills

Required:AI/ML EngineeringAdversarial ML MindsetAgentic Frameworks SecurityInfrastructure SecurityPragmatic Risk AssessmentSoftware Development & AutomationTranslational Communication
Last updated Jul 15, 2026. Interested? Apply on the company site.

About Isomorphic Labs

Reimagining Drug Discovery Process with AI

Isomorphic Labs is building a future where frontier AI can help to unlock deeper scientific insights, faster breakthroughs, and life-changing medicines.

AIBiotechnologyDrug DiscoveryPharmaceuticalsliquid-ai-recruiting-target
Company profileWebsite

More open roles at Isomorphic Labs