Senior Security Engineer (AI Safety)

Location: Lausanne; London

Company: hirify.global

hirify.global applies frontier AI to accelerate drug discovery and advance digital biology.

What you will do

• Conduct adversarial threat modeling for AI/ML vulnerabilities and build a comprehensive risk management framework for an AI-powered life sciences platform.
• Establish granular protection for ML model artifacts (weights, code, and training data), including inventory and classification.
• Design and deploy LLM/agentic guardrails: sandboxing and real-time monitoring across an LLM ecosystem (including ADK, MCP, and autonomous agentic workflows).
• Implement security controls across the ML lifecycle, from data ingestion and training pipeline integrity to inference runtime controls.
• Lead AI-specific incident response and automate threat hunting, anomaly detection, and signatureless mitigation for LLMs.
• Automate compliance and governance metrics (e.g., EU AI Act) and help operationalize AI Safety standards in coordination with Legal/Compliance and external partners.

Requirements

• Deep conceptual and practical understanding of deep learning frameworks and large-scale cloud training/inference infrastructure, plus LLM ecosystem experience.
• Strong familiarity with AI security threat vectors (e.g., prompt injection, model inversion, data poisoning) and relevant frameworks (e.g., OWASP Top 10 for LLMs, MITRE ATLAS).
• Proven experience securing agentic frameworks (ADK, MCP) and implementing agent-to-agent identity and access controls.
• Solid cloud security proficiency (GCP preferred), including container security, multi-cloud/SaaS integrations, and network isolation.
• Ability to define and execute pragmatic mitigation strategies balancing security posture with high-velocity research needs.
• Hybrid working: able to come into the office 3 days a week (Tuesday, Wednesday, and one other day depending on the team).

Nice to have

• Experience with AI red teaming and simulated attacks against LLMs, agent networks, and ML backends.
• Background in regulated environments (BioTech/Pharma/Deep Tech) and GxP-related data integrity/IP protection.
• Academic background (BSc/MSc/PhD) in Computer Science, Machine Learning, Cybersecurity, or a related quantitative field.
• Relevant security/cloud certifications (e.g., OSCP, Professional Cloud Security Engineer) or specialized ML security training.

Culture & Benefits

• Hybrid model designed to support knowledge sharing and in-person collaboration.
• Values-driven culture focused on curiosity, creativity, care, bravery, determination, and collaboration.
• Emphasis on learning, shared knowledge, and support for employees to thrive.
• Equal employment opportunity commitment regardless of protected characteristics.