🕒 yesterday
Secure AI-enabled products and agent workflows by managing third-party model risks, enforcing data isolation and least-privilege access, and testing defenses against prompt injection and misuse.
AI Security Engineer
🕒 yesterday
Application SecurityProduct SecurityAI System SecurityThird-party LLM Integrations
📜 Description
- Assess customer data shared with third-party model vendors, including minimization, retention, logging, vendor controls, and approved use.
- Design least-privilege controls for AI agent permissions, tools, actions, and system access.
- Implement and test tenant and user data isolation across prompts, conversation history, retrieval, memory, and connected services.
- Threat model and test prompt injection and indirect injection through documents, retrieved content, links, and other untrusted inputs.
- Partner with Product and Engineering on safe document ingestion, content handling, output validation, and approval for sensitive actions.
- Support AI technology risk assessments, control evidence, remediation, security testing, monitoring, and incident response.
🛠️ Requirements
- Degree in Computer Science, Cybersecurity, AI, or a 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, cross-user data leakage, excessive agent permissions, and vendor data disclosure risks.
- Programming or scripting skills; Python and TypeScript/Node.js preferred, plus APIs and AWS or GCP.
- Strong English communication and ability to collaborate across Product, Legal, Compliance, Data, and Engineering.
Full job description
About BJAK
The original mission of BJAK is we believe people deserve smarter ways to plan, save and grow their money. This is the origin of our name.
Started in 2019, we built the first mobile-first, insurance platform, enabling insurance to be accessible online by millions in the region. Today, its the leading insurance platform in Southeast Asia.
Today, we are expanding ways to help people in the region — this includes spending, saving, investing, exchanging, travelling, and more. Our mission is help people get more from their money every day.
We have teams working around the world, with over 20 nationalities from our offices and remotely, who truly enjoys their work. We are looking for the most talented and driven people we can find. We are looking for people who work for their passion, not counting hours. Who loves building great next-generation products, not status quo. Who cares about redefining how everyone around us can get the best financial applications, not for an exclusive few.
If you're this person, we'd love to talk to you.
The Role
Secure BJAK's AI-enabled products and agent workflows using third-party models. Focus on customer data shared with model providers, agent permissions, user data isolation, and prompt injection through uploaded documents and other untrusted content.
What You Will Build
Assess customer data sent to third-party model vendors, including minimization, vendor controls, retention, logging, and approved use.
Design controls limiting AI agent permissions, tools, actions, and system access using least privilege and explicit authorization.
Implement and test tenant and user data isolation across prompts, conversation history, retrieval, memory, and AI-connected services.
Threat model and test prompt injection and indirect injection through uploaded documents, retrieved content, links, and other untrusted inputs.
Partner with Product and Engineering on safe document ingestion, content handling, output validation, and approval for sensitive actions.
Support SC TRM and BNM RMiT for AI technology risks, including assessments, third-party oversight, control evidence, and remediation.
Build security tests, monitoring, and response procedures for AI misuse, data exposure, unauthorized actions, and vendor incidents.
What We Look For
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, preferably Python and TypeScript/Node.js, plus APIs and AWS or GCP.
Able to collaborate with Product, Legal, Compliance, Data, and Engineering on practical controls and risk communication.
Language
English is our main working language across global teams. Strong English communication is required.
Similar jobs
Search more Cybersecurity Engineer jobs🕒 yesterday
Secure AI-enabled products and agent workflows by managing third-party model data risks, limiting agent permissions, enforcing user data isolation, and testing defenses against prompt injection.
🕒 7 days ago
Architect application security tooling and embed security in development workflows across SaaS platforms, partnering with developers and operations on testing, threat modeling, vulnerability remediation, automation, and incident response.
🕒 8 days ago
Design and implement security and privacy architecture for an AI-native phone, controlling how agents access personal data and system services while protecting users from AI-specific threats.
🕒 9 days ago
Build and operate security controls across cloud infrastructure, applications, employee systems, and AI tools, investigating threats, automating defenses, and driving findings through remediation.