Senior Security Engineer (AI Safety), London, Lausanne

The role

You will architect, secure, and future-proof an AI-first platform and autonomous agentic workflows. You will design risk management frameworks, establish model artifact protection, and implement security controls for distributed training and inference infrastructure.

What you will do

• Conduct threat modeling focused on AI/ML vulnerabilities
• Establish a protection framework for ML models weights, code, and training data
• Design and deploy guardrails and monitoring for LLM ecosystems and agentic workflows
• Implement security controls across the ML lifecycle
• Act as technical expert for AI security incidents
• Automate risk posture monitoring and compliance metrics
• Implement AI Safety standards

Required qualifications

• Deep conceptual and practical understanding of deep learning frameworks (e.g., JAX, PyTorch, TensorFlow)
• Understanding of large-scale cloud training or inference infrastructure and LLM ecosystems
• Familiarity with AI security threat vectors (prompt injection, model inversion, data poisoning)
• Familiarity with frameworks like OWASP Top 10 for LLMs or MITRE ATLAS
• Experience securing agentic frameworks (ADK, MCP) and implementing agent-to-agent identity and access controls
• Proficiency in cloud platform security (GCP preferred)
• Proficiency in container security, multi-cloud/SaaS integrations, and network isolation boundaries
• Ability to execute pragmatic mitigation strategies
• Ability to write production-grade code (Python preferred)
• Skills in translating complex machine learning risks into actionable engineering tasks

Nice to have

• Experience conducting empirical vulnerability research or simulated attacks against LLMs, agent networks, and core ML backends
• Prior exposure to BioTech, Pharma, and/or Deep Tech industries
• BSc, MSc, or PhD in Computer Science, Machine Learning, Cybersecurity, or a related quantitative field
• Relevant security or cloud credentials (e.g., OSCP, Professional Cloud Security Engineer)
• Specialized training in ML security

About the company

Isomorphic Labs (IsoLabs) was launched in 2021 to advance human health by building on and beyond the Nobel-winning AlphaFold system. The company uses AI to model complex biological phenomena to help design novel molecules and develop medicines.