Senior AI Security Researcher — FULL_TIME
Looking for your next role as a Senior AI Security Researcher? Take the next step in your career with an established company in Singapore.
Key Responsibilities
- Proactively identify and exploit vulnerabilities in internet-facing and internal systems.
- Deliver working proofs of concept, clear impact assessments, and actionable findings.
- Conduct offensive security testing of AI products and infrastructure.
- Execute jailbreaks, prompt injection, model evasion, data exfiltration, and API abuse tests.
- Evaluate security for MCP, plugin, and tool-calling integrations.
- Build and automate AI-assisted security research workflows and agents using models, APIs, and tools.
- Research weaknesses in models and surrounding infrastructure to produce high-quality, CVE-ready findings.
- Design, implement, and evaluate guardrails and defensive controls such as filtering, monitoring, and anomaly detection.
- Partner with product and engineering teams to turn findings into practical requirements and mitigations.
- Communicate technical findings, risk, and impact to cross-functional teams and stakeholders.
Job Requirements
- You hold a Bachelor's degree in computer science or a related field, or possess equivalent practical experience.
- You have at least 4 years of offensive security experience, including penetration testing, red teaming, or API security testing.
- You must have a track record of at least one published CVE or a verified HackerOne bug-bounty finding.
- You demonstrate expertise through published security research, conference presentations, or a technical blog.
- You have at least 1 year of hands-on experience in AI security testing, including prompt injection and data leakage mitigation.
- You possess demonstrated ability in building autonomous agents that interact with AI to test systems.
Job Details
- Location: Central Region.
- Job Type: Full Time.
What's on Offer
