AI Security Research Engineer Job – OneSpotAI – Bengaluru

OneSpotAI is hiring an AI Security Research Engineer Intern to work on security testing and research for AI systems. The role focuses on finding weaknesses in AI models, agents, RAG applications, APIs and connected tools.

The candidate will help identify security risks such as prompt injection, jailbreaks, data leakage and misuse of AI agents, and document findings with practical remediation guidance.

Key Responsibilities:

Test AI systems for security vulnerabilities.
Perform prompt injection and jailbreak testing.
Research AI agent and tool-abuse risks.
Test RAG, LLM applications and API security.
Build internal security testing and evaluation tools.
Document security findings and suggested fixes.

Requirements:

Strong interest in AI security and cybersecurity.
Good programming skills, preferably Python.
Understanding of LLM applications, AI agents, APIs and RAG.
Basic knowledge of threat modeling, red teaming or vulnerability research.
Good analytical and writing skills.
Hands-on projects, CTFs, blogs or open-source work are a plus.