Senior AI Security Engineer - Hybrid Life Sciences

Isomorphiclabs; Lausanne; Hybrid; CHF 140.000 - 210.000; Vollzeit

Zusammenfassung

Isomorphic Labs is seeking a Senior AI Security Engineer to defend an AI-first drug discovery platform. Reporting to the CISO, you will architect risk management for AI systems, secure model artifacts, and embed defense mechanisms across training and inference workflows.

You will lead AI-specific incident response, automate threat hunting, and ensure compliance with evolving global regulations while collaborating with Legal, Compliance, and external partners like Google DeepMind.

Qualifikationen

• Deep conceptual and practical understanding of deep learning frameworks (e.g., JAX, PyTorch, TensorFlow) and large-scale cloud training or inference.
• Strong familiarity with AI security threat vectors (prompt injection, model inversion, data poisoning) and frameworks like OWASP Top 10 for LLMs or MITRE ATLAS.
• Proven experience securing agentic frameworks (ADK, MCP) and implementing robust agent-to-agent identity and access controls.
• Solid proficiency in cloud platform security (GCP preferred), container security, multi-cloud/SaaS integrations.
• Pragmatic risk assessment with ability to balance security posture and high-velocity research needs.
• Production-grade coding ability (Python) to build security tooling and enforce policy layers.
• Excellent translation of ML risks into actionable engineering tasks for leadership.

Aufgaben

• Adversarial Threat Modeling: Conduct threat modeling focused on AI/ML vulnerabilities for an AI-powered life sciences platform.
• Model Artifacts Protection: Establish inventory, classification and protection for ML model weights, code and data.
• Agentic AI & LLM Guardrails: Design deploy scalable guardrails, sandboxing, and monitoring for LLM ecosystem (ADK, MCP, autonomous workflows).
• Collaborative Security Engineering: Partner with ML researchers and platform engineers to implement security controls across the ML lifecycle.
• Model-Driven Incident Response: Lead AI security incidents with advanced ML techniques for threat hunting and anomaly detection.
• Compliance & Governance Automation: Automate risk posture monitoring and compliance metrics per EU AI Act and other regs.
• AI Safety Frameworks: Implement Isomorphic Labs' AI Safety standards with Legal, Compliance, and partners like Google DeepMind.

Kenntnisse

AI/ML Engineering

Adversarial ML Mindset

Agentic Frameworks Security

Infrastructure Security

Pragmatic Risk Assessment

Software Development & Automation

Translational Communication

Ausbildung

PhD in Computer Science / ML / Cybersecurity

Advanced Certifications in Security / Cloud

Jobbeschreibung

Isomorphic Labs is seeking a Senior AI Security Engineer to defend an AI-first drug discovery platform. Reporting to the CISO, you will architect risk management for AI systems, secure model artifacts, and embed defense mechanisms across training and inference workflows.

You will lead AI-specific incident response, automate threat hunting, and ensure compliance with evolving global regulations while collaborating with Legal, Compliance, and external partners like Google DeepMind.