AI Security Engineer

The role

This person will secure AI-enabled products and agent workflows using third-party models. They will focus on customer data, agent permissions, user data isolation, and prompt injection.

What you will do

• Assess customer data sent to third-party model vendors
• Design controls limiting AI agent permissions, tools, actions, and system access
• Implement and test tenant and user data isolation
• Threat model and test prompt injection and indirect injection
• Partner with Product and Engineering on safe document ingestion and output validation
• Support SC TRM and BNM RMiT for AI technology risks
• Build security tests, monitoring, and response procedures for AI misuse and data exposure

Required qualifications

• Degree in Computer Science, Cybersecurity, AI, or related field, or equivalent experience
• 3+ years in application security, product security, security engineering, or AI system security
• Experience implementing or owning SC TRM and BNM RMiT controls, technology risk, or regulatory control evidence
• Understanding of third-party LLM integrations, model APIs, agent tools, RAG, and AI application architectures
• Knowledge of prompt injection, indirect injection, cross-user data leakage, excessive agent permissions, and vendor data disclosure risks
• Programming or scripting skills
• APIs and AWS or GCP
• Strong English communication

Nice to have

• Python
• TypeScript/Node.js

About the company

BJAK is a mobile-first insurance platform in Southeast Asia. The company aims to help people plan, save, and grow their money.