Builds and trains AI agents for cybersecurity using LLM post-training, reinforcement learning, and agentic systems research.

Designs and deploys large-scale AI systems for security event analysis, anomaly detection, and threat prioritization at enterprise scale.

Identifies and mitigates security vulnerabilities in LLMs and AI agents through threat research and red-teaming.

Researches vulnerabilities, develops exploits, and analyzes malicious activity to support threat intelligence operations.

Lead mechanistic interpretability and alignment research for security-domain AI systems to detect misuse and ensure safe model behavior.

Leads post-training and agentic AI research for security-domain models, designing reward systems and agent harnesses while managing a research team.

Develops predictive models and analytics solutions for enterprise business functions while mentoring junior data scientists.

Investigates cloud intrusions using logs and reverse engineering to develop threat intelligence and detection signatures.

Leads malware analysis research, mentors junior researchers, and architects automation solutions for threat detection at scale.

Research and prototype generative AI solutions for cybersecurity threat detection and response capabilities.

Research and analyze malware families while developing tools for threat intelligence pipelines.