Senior AI Security Researcher - Offensive AI Threat Hunter

AGODA COMPANY PTE. LTD.; Singapore; On-site; SGD 160,000 - 210,000; Full time

Job summary

AGODA COMPANY PTE. LTD. seeks a Senior AI Security Researcher in Singapore to aggressively find real-world vulnerabilities and document CVE-quality findings.

You will build autonomous agents that hunt for bugs by interacting with AI systems, develop AI-driven offensive workflows, and jailbreak AI models. Strong hands-on security background and ability to communicate risk to leadership are essential. The role emphasizes external attack paths, model/test automation, and collaboration with product

Qualifications

• 2-7 years in offensive cybersecurity.
• Published CVE(s).
• Strong offensive security knowledge: API security testing, red teaming or adversarial testing.
• Hands-on jailbreak experience (prompt injection, data leakage, safety bypasses).
• Ability to coordinate with multiple teams and present to C-level stakeholders.
• Good communication skills in English.
• Experience handling and maintaining production-level code.

Responsibilities

• Proactively find, exploit, and document real-world vulnerabilities with external attack paths.
• Document CVE-quality research outcomes and drive fixes.
• Build autonomous agents that hunt and iterate with AI models and tools.
• Develop AI-driven offensive workflows and model orchestration for continuous hunting.
• Design, execute, and document jail breaks and prompt injections against AI systems.
• Assess MCP-based systems and tool-calling ecosystems for vulnerabilities.
• Automate security testing workflows involving multiple models, APIs, and tools.
• Perform offensive security testing and red teaming of AI-driven products.

Skills

Offensive security

API security testing

Red teaming

Prompt injection

Model security

Documentation

Education

Bachelor's degree in CS

Job description

AGODA COMPANY PTE. LTD. seeks a Senior AI Security Researcher in Singapore to aggressively find real-world vulnerabilities and document CVE-quality findings.

You will build autonomous agents that hunt for bugs by interacting with AI systems, develop AI-driven offensive workflows, and jailbreak AI models. Strong hands-on security background and ability to communicate risk to leadership are essential. The role emphasizes external attack paths, model/test automation, and collaboration with product