TixelJobs
G
GovTech Singaporevia Greenhouse

Senior AI Security Consultant

SingaporePosted 1mo ago
OtherSeniorFull-time

About the Role

As the Senior AI Security Consultant for the BusinessSG initiative, you will be the primary security architect guiding our transition to a proactive AI-driven platform. You will be embedded within a 10-man Discovery Squad, working alongside AI engineers and product leads to ensure that autonomous AI workflows—operating via messaging interfaces and a unified data hub—are secure, transparent, and resilient. 

Your mission is to ensure every AI action is auditable and non-repudiable, protecting multi-agency data sources while maintaining the highest standards of public trust. 

 

Key Responsibilities 

  1. Security Architecture & Threat Modeling 
  • System Design: Lead the design of security guardrails for AI agents to prevent them from taking unauthorized legal or financial actions. 
  • Threat Modeling: Map out potential risks for autonomous AI, such as users trying to "hijack" the agent's intent or tricking it into accessing data it shouldn't. 
  • Human-in-the-Loop: Design workflows that ensure high-stakes AI decisions (like grant recommendations) cannot proceed without explicit, authenticated human approval. 
  1. Reliable Audit & Explainability 
  • Audit Trails: Build a "Chain of Custody" for AI decisions by logging what the agent "thought," what specific data it retrieved, and which model version was used. 
  • Reproducibility: Ensure that AI actions are documented well enough to be reconstructed and explained to auditors or stakeholders. 
  • Data Governance: Ensure the AI only accesses integrated agency data on a strict "need-to-know" basis. 
  1. Testing & Advanced Privacy (Preferred)
  • Security Testing: Conduct proactive testing to find vulnerabilities in how the AI processes instructions or uses external tools. 
  • Share