AI Security Researcher (Bangkok Based, Relocation provided)
Agoda
10 days ago
Bangkok, Thailand
Mid Level / Senior
Responsibilities
- Design, execute, and document offensive security techniques against AI systems.
- Assess and compromise Model Context Protocol (MCP)–based systems.
- Build and automate security testing workflows for LLM models and APIs.
- Perform red teaming of AI-driven products, including API manipulation.
- Research security weaknesses in LLMs and Generative AI systems.
- Contribute to the design and testing of safety and security guardrails.
- Propose and evaluate defensive controls for AI systems.
- Translate research findings into engineering requirements.
- Stay current with AI security standards and threat models.
- Produce technical documentation and share knowledge on AI security.
Requirements
- Bachelor's degree in Computer Science or related field.
- 2-5 years of experience in offensive cybersecurity.
- Good communication skills in English.
- Deep understanding of LLMs and Generative AI architectures.
- Hands-on experience with jailbreaking and red-teaming AI agents.
- Strong background in offensive security and API security testing.
- Prior experience in red teaming or penetration testing.
- Bug bounty or HackerOne experience is a plus.
- Scripting knowledge in Python or PowerShell.
Tech Stack
PowerShellPython
Categories
AI & MLSecurity