AI Analyst Intern (Research, build, and experiment with LLMs and agentic AI for cybersecurity protocols)
Conducted research and experimental work using LLMs and agentic AI to support cybersecurity protocols and tools. Contributed to development of intelligent multi-agent workflow automation for optimizing cyber defense. Focused on evaluation and assessment of AI-driven outputs to improve performance and reliability across security workflows. • Worked on AI-powered multi-agent systems and automated workflows. • Experimented with LLM/agentic AI approaches for cybersecurity use cases. • Helped iterate on system behavior based on observed results. • Supported research activities aimed at improving downstream AI effectiveness.