At OneSpotAI, we are building security infrastructure for AI. We help companies in healthcare, finance, and logistics find and fix weaknesses in their AI systems before attackers do. The Role Research Engineer Intern. You will find vulnerabilities in AI agents and LLM applications, then build the fixes and prove they hold. What You Will Do
• Break AI agents and LLM apps (prompt injection, tool misuse, data leakage, privilege escalation)
• Find the root cause of each failure
• Build fixes: guardrails, permission boundaries, detection logic
• Build retest harnesses so fixes stay fixed
• Write findings engineers can act on quickly What We Are Looking For
• Solid Python
• Hands-on experience with LLM apps, agents, RAG, or MCP
• Basic knowledge of threat modeling, red teaming, or vulnerability research
• Proof of work: GitHub projects, CTF writeups, blog posts, or research notes What You Get
• Fully remote
• Flexible hours
• Stipend at the top of the market for this kind of role
• Direct work with the founding team
• Your work goes into production Apply through LinkedIn or email us at [email protected]

📌 Research Engineer Intern, AI Security (Bengaluru)
🏢 OneSpotAI
📍 Bengaluru