Research Intern in Agentic AI Security Frameworks

Tasks

• Conduct security analysis and verification
• Contribute to research publications and patents
• Develop algorithms, tools, and systems for secure agents
• Participate in fundamental AI security research
• Prototype security primitives for AI agents
• Simulate attacks on AI systems

Perks/Benefits

• N/A

Skills/Tech-stack

AI | C++ | Communication skills | Huggingface | Linux | Prototyping | PyTorch | Python | Security | System analysis