Senior AI Security Engineer

📋 Description

• Research agentic threats, incl. prompt injection, context poisoning, adversarial content.
• Architect scalable agentic workflows; secure agent-to-web interactions.
• Develop detection and mitigation techniques for malicious prompts and adversarial behavior.
• Implement security controls within agent runtimes for safe reasoning over data.
• Collaborate with engineers to productionize security mechanisms.
• Proactively threat model AI risks to anticipate future issues.

🎯 Requirements

• BSc in CS or significant high‑scale cloud exp; MSc/PhD is a plus.
• 3+ years in applied AI with production AI systems; agentic experience a plus.
• Expert Python; Kubernetes and cloud‑native orchestration; data modeling and VCS.
• Significant experience in cybersecurity or browser tech is preferred.
• Deep understanding of prompt engineering and exploitation in agentic systems.
• Able to explore ambiguity, experiment, and iterate toward effective security solutions.

🎁 Benefits

• Collaborative culture with shared core values.
• Open communication and opportunities to take initiative.
• Open environment to learn and grow within security-focused teams.