Senior Security Engineer (AI Safety), London, Lausanne
Salary not listed • Lausanne; London • Full-time
Posted 4mo ago
This job has been open for more than 60 days. It may no longer be actively hiring, so check with the company before putting a lot into an application.
Job Location
Lausanne; London
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Engineer
About the job
Isomorphic Labs is at the forefront of applying artificial intelligence to accelerate drug discovery and develop life-changing medicines. We are building a pioneering AI-first platform and autonomous agentic workflows to drive the next generation of drug discovery pipelines. As a Senior AI Security Engineer, you will operate at the intersection of AI and Cybersecurity, architecting and securing our platform. Your mission is to design custom risk management frameworks for the AI threat landscape in life sciences, establish governance over model artifacts, and embed security controls into our AI infrastructure. You will lead AI-specific incident response and pioneer model-driven defense mechanisms to safeguard intellectual property and accelerate innovation.
Responsibilities
- Conduct threat modeling focused on AI/ML vulnerabilities and engineer a risk management framework for an AI-powered life sciences platform.
- Establish an inventory, classification, and protection framework for ML models, weights, code, and training data.
- Design and deploy scalable guardrails, sandboxing, and monitoring controls for LLM ecosystems, including ADK, MCP, and autonomous agentic workflows.
- Partner with AI teams to design and implement security controls across the ML lifecycle, from data ingestion to inference runtime.
- Serve as the technical expert for AI security incidents, deploying ML techniques for automated threat hunting and mitigation specific to LLMs.
- Automate risk posture monitoring and continuous compliance metrics to align AI architectures with global regulations.
- Pioneer the implementation of AI Safety standards in coordination with Legal, Compliance, and external partners.
Requirements
- Deep understanding of deep learning frameworks (JAX, PyTorch, TensorFlow), large-scale cloud training/inference infrastructure, and LLM ecosystems.
- Familiarity with AI security threat vectors (e.g., prompt injection, data poisoning) and frameworks like OWASP Top 10 for LLMs or MITRE ATLAS.
- Experience securing agentic frameworks (ADK, MCP) and implementing agent-to-agent (A2A) identity and access controls.
- Proficiency in cloud platform security (GCP preferred), container security, and network isolation.
- Ability to define and execute pragmatic mitigation strategies balancing security with research needs.
- Ability to write production-grade code (Python preferred) for security tooling and automation.
- Exceptional skills in navigating ambiguity and building relationships with AI researchers.