Senior AI Security Researcher — Offensive Security Leader

AGODA COMPANY PTE. LTD.; Singapore; Sur place; SGD 180 000 - 320 000; Plein temps

Résumé du poste

Agoda Company Pte. Ltd. is seeking a Staff AI Security Researcher based in Singapore with a strong offensive security background and CVE publication history. The role focuses on AI-assisted hunting, jailbreaks, and building autonomous agents to find real vulnerabilities before attackers do.

You will define the AI security agenda, lead cross-team efforts, and raise the bar for exploitability and impact while shaping practical security controls around AI systems.

Qualifications

• Bachelor's in Computer Science or related field.
• 7–12 years in offensive cybersecurity with impactful findings.
• Published CVE(s) including at least one vendor fix or product change.
• Strong offensive security knowledge: API testing and manipulation.
• Hands-on jailbreak experience (prompt injection, data leakage, etc.).

Responsabilités

• Set AI security research agenda and prioritize attack paths and surfaces.
• Proactively find, exploit, and document real-world vulnerabilities.
• Produce CVE-quality research outcomes with real impact.
• Own findings from PoC to engineering fix and verification.
• Build autonomous agents and hunting workflows for continuous testing.
• Raise researcher standards and mentor others on exploitability and write-ups.
• Translate research into practical engineering requirements for fixes.

Connaissances

Offensive security

CVE research

AI security

Red teaming

POC development

Formation

Bachelor's in CS or related

Outils

Jupyter notebooks

Orchestration frameworks

Description du poste

Agoda Company Pte. Ltd. is seeking a Staff AI Security Researcher based in Singapore with a strong offensive security background and CVE publication history. The role focuses on AI-assisted hunting, jailbreaks, and building autonomous agents to find real vulnerabilities before attackers do.

You will define the AI security agenda, lead cross-team efforts, and raise the bar for exploitability and impact while shaping practical security controls around AI systems.