Senior Security Engineer (AI Safety), London or Lausanne
HybridLausanne, Vaud, Switzerland
Job Summary
Conduct adversarial threat modeling for AI/ML vulnerabilities and engineer comprehensive risk management frameworks tailored to an AI-powered life sciences platform. Partner with ML researchers to establish granular protection frameworks for model artifacts, weights, and training data while deploying scalable guardrails and sandboxing for autonomous agentic workflows. Act as the primary technical expert for AI security incidents, automating threat hunting and mitigation using machine learning techniques to safeguard intellectual property. Bridge the gap between complex AI architectures and emerging global regulations by automating risk posture monitoring and continuous compliance metrics. Report directly to the CISO to architect and future-proof the pioneering AI-first platform driving next-generation drug discovery pipelines.
Required Qualifications
- Deep conceptual and practical understanding of deep learning frameworks (e.g., JAX, PyTorch, TensorFlow)
- Large-scale cloud training or inference infrastructure experience
- LLM ecosystems experience
- Strong familiarity with AI security threat vectors (prompt injection, model inversion, data poisoning)
- Familiarity with frameworks like OWASP Top 10 for LLMs or MITRE ATLAS
- Proven experience securing agentic frameworks (ADK, MCP)
- Experience securing agentic first infrastructure
- Implementing robust agent-to-agent (A2A) identity and access controls
- Solid proficiency in cloud platform security (GCP preferred)
- Container security experience
- Multi-cloud/SaaS integrations experience
- Strict network isolation boundaries experience
- Proven ability to define and execute pragmatic mitigation strategies
- Ability to write production-grade code (Python preferred)
- Exceptional skills in navigating ambiguity
- Building trusted relationships with AI researchers
- Translating complex machine learning risks into actionable engineering tasks for leadership
Desired Qualifications
- Experience conducting empirical vulnerability research
- Executing simulated attacks against LLMs
- Attacking agent networks
- Attacking core ML backends
- Prior exposure to BioTech, Pharma, and/or Deep Tech industries
- Data integrity experience
- Intellectual property protection experience
- Regulatory compliance (GxP) experience
- 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
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.