Senior AI Security Consultant

SCIENTE; Singapore; In loco; SGD 140.000 - 240.000; Tempo pieno

Descrizione del lavoro

SCIENTE seeks a Senior AI Security Consultant to architect and safeguard autonomous AI systems across multi-agency platforms. You will lead security architecture, threat modeling, and end-to-end audit trails to ensure auditable, privacy-preserving operations.

The role requires 6–10 years in cybersecurity with 2–3 years in AI/ML or LLM security, and deep expertise in AI governance, ABAC, and data protection. Singapore standards alignment is essential.

Competenze

• 6–10 years in Cybersecurity with 2–3 years in AI/ML or LLM security required.
• Strong expertise in agentic AI systems and API-driven automation security demanded.
• Deep understanding of LLM risks (prompt injection, data leakage, RAG security).
• Experience with threat modeling and secure system design for AI workflows.
• Proficiency in identity, access control, and policy-based authorization (ABAC).
• Knowledge of audit logging, traceability, and reproducibility in AI systems.
• Familiarity with data governance and privacy controls for sensitive data environments.
• Understanding of Singapore public sector standards (IM8, Model AI Governance).
• Experience with security testing, vulnerability assessment, and adversarial analysis.

Mansioni

• Lead security architecture design for autonomous AI systems and define guardrails to prevent unauthorized actions.
• Conduct threat modeling to identify risks such as prompt injection and data access violations.
• Design and enforce human-in-the-loop controls for high-risk AI decisions.
• Implement end-to-end audit trails capturing AI decisions, data usage, and model versions for traceability.
• Ensure reproducibility and explainability of AI outputs for audits and compliance reviews.
• Enforce strict data governance and least-privilege access across multi-agency data sources.
• Perform proactive security testing, vulnerability assessments, and adversarial simulations on AI workflows.
• Implement advanced privacy controls to protect sensitive business and government data.
• Collaborate with AI engineers and product teams in an agile environment to balance speed and security.
• Translate complex AI security risks into clear insights for senior stakeholders.

Conoscenze

Cybersecurity experience

AI/ML or LLM security

Agentic AI systems

API-driven security

LLM risks awareness

Threat modeling

Secure system design

Identity and access control

Policy-based authorization (ABAC)

Audit logging & traceability

Data governance & privacy controls

Singapore standards (IM8)

Security testing & vulnerability

Adversarial analysis

Descrizione del lavoro

We are seeking a Senior AI Security Consultant to architect and safeguard autonomous AI systems, ensuring secure, auditable, and privacy-preserving operations across multi-agency platforms.

Mandatory Skill-set

• 6–10 years in Cybersecurity with 2–3 years in AI/ML or LLM security;
• Strong expertise in agentic AI systems and API-driven automation security;
• Deep understanding of LLM risks (prompt injection, data leakage, RAG security);
• Experience with threat modeling and secure system design for AI workflows;
• Proficiency in identity, access control, and policy-based authorization (e.g., ABAC);
• Knowledge of audit logging, traceability, and reproducibility in AI systems;
• Familiarity with data governance and privacy controls for sensitive data environments;
• Understanding of Singapore public sector standards (IM8, Model AI Governance Framework);
• Experience with security testing, vulnerability assessment, and adversarial analysis.

Desired Skill-set

• Experience with immutable logging, digital forensics, or building tamper-proof audit trails;
• Prior exposure to public sector or Smart Nation initiatives, with strong alignment to governance and compliance frameworks.

Responsibilities

• Lead security architecture design for autonomous AI systems, defining guardrails to prevent unauthorized actions;
• Conduct threat modeling to identify risks such as prompt injection, misuse of AI agents, and data access violations;
• Design and enforce human-in-the-loop controls for high-risk AI decisions;
• Implement end-to-end audit trails capturing AI decisions, data usage, and model versions for traceability;
• Ensure reproducibility and explainability of AI outputs for audits and compliance reviews;
• Enforce strict data governance and least-privilege access across integrated multi-agency data sources;
• Perform proactive security testing, vulnerability assessments, and adversarial simulations on AI workflows;
• Implement advanced privacy controls to protect sensitive business and government data;
• Collaborate with AI engineers and product teams in an agile discovery environment to balance speed and security;
• Translate complex AI security risks into clear, actionable insights for senior stakeholders.

Confidentiality is assured, and only shortlisted candidates will be notified for interviews.