🛠 Tech Stack

💼 About This Role

You'll research and design novel techniques to detect and mitigate adversarial threats against AI agents. You will work with engineering teams to translate security research into practical, deployable controls for agents interacting with untrusted web content.

🎯 What You'll Do

• **Research emerging attack vectors** against AI agents (prompt injection, context poisoning).
• **Design and prototype novel detection** and mitigation techniques for adversarial behaviors.
• **Implement security controls** within agentic runtimes for safe reasoning over external data.
• **Partner with applied engineers** to integrate research into production systems.

📋 Requirements

• BSc in Computer Science or equivalent high-scale cloud engineering experience.
• 3+ years in applied AI with production deployment of high-scale AI systems.
• Expert-level Python and deep experience with k8s and cloud-native orchestration.
• Significant experience in cybersecurity or browser-related technologies.

✨ Nice to Have

• Hands-on experience with orchestration frameworks like LangChain or AutoGen.
• Experience building immutable event streams and high-speed data pipelines.
• Understanding of DOM or Accessibility Tree programmatic manipulation.

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 🏥 Health insurance (medical, dental, vision)
• 💰 Equity (stock options)
• 📚 Learning and development opportunities
• 🤝 Collaborative culture with core values

🚩 Heads Up

• Job description is very long and includes extensive company background.
• Requirements mention '3+ years' but title says 'Senior', which may imply more experience expected.
• Role blends research and engineering which may lead to scope creep.