Serena Lekhrajani
Software Engineer II - Microsoft Security CISO
Bellevue, Washington, United States
Actions
Serena Lekhrajani is a Software Engineer at Microsoft with experience building large-scale, distributed systems across Generative AI and cybersecurity — including threat actor remediation platforms, unified threat detection infrastructure, and AI-powered productivity experiences. She is an inventor on a Microsoft patent and has authored peer-reviewed research at IEEE conferences spanning AI, deep learning, IoT, data analytics, and cybersecurity.
Beyond her technical work, Serena is driven by a conviction that the measure of success in tech isn't just what you build — it's how many people you bring with you. She mentors early-career engineers, judges student competitions, and speaks at STEM panels, consistently showing up for the next generation of women in tech at every stage of their journey.
Links
Area of Expertise
Topics
From Security Graphs to Insights: Building an Enterprise Security Copilot with MAF
Security teams don't struggle because they lack data—they struggle because connecting thousands of signals into meaningful investigations is slow, manual, and requires deep domain expertise.
What if AI agents could orchestrate those investigations instead of simply answering questions? In this session, I'll share how we built an enterprise Security Graph Copilot for Microsoft's CISO organization using the Microsoft Agent Framework. Rather than relying on a single LLM, the solution coordinates specialized agents that understand user intent, plan investigations, retrieve and reason over security graph data, invoke domain-specific tools, and synthesize actionable results.
You'll learn the architecture behind a production multi-agent system, the design patterns that make agent orchestration reliable, approaches for integrating enterprise data sources and tools, techniques for grounding LLM responses with graph-based context, and the engineering tradeoffs we encountered while building an AI assistant for real-world security operations. Whether you're building enterprise copilots or exploring agentic AI, you'll leave with practical patterns you can apply to your own AI applications.
Beyond Chat: Designing Collaborative AI Workspaces for Teams
AI assistants have transformed individual productivity, but true organizational impact requires moving beyond user-centric experiences. This talk explores how workspace-centric architectures enable teams to collaboratively manage knowledge, conversations, documents, and AI capabilities within shared contexts. Attendees will gain practical insights into designing scalable permission models, context-aware AI systems, and collaborative workflows that make AI more useful for teams, not just individuals. The session focuses on architectural patterns, design decisions, and lessons learned that can be applied across enterprise AI and collaboration platforms.
Organizations are rapidly moving from experimenting with AI assistants to integrating AI into team workflows. However, most systems are still designed around individual users. This session addresses a timely challenge facing the industry: designing AI experiences that scale from personal productivity to collaborative intelligence while maintaining governance, usability, and trust.
Serena Lekhrajani
Software Engineer II - Microsoft Security CISO
Bellevue, Washington, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top