Khushan Adatiya
Senior Software Engineer, Google | Distributed Systems & AI Architect
San Francisco, California, United States
Actions
Khushan Adatiya is a Senior Software Engineer at Google, specializing in distributed systems, cloud architecture, and AI-driven platforms. With 10+ years of experience, he has led the design of high-throughput, production-critical systems, including API management, anomaly detection, and observability pipelines. Khushan combines expertise in microservices, Kubernetes, cloud-native technologies, and generative AI, including AI agents and retrieval-augmented reasoning systems. He is passionate about building scalable, secure, and intelligent cloud solutions. Khushan regularly mentors students and engineers and delivers technical talks on AI architectures, cloud observability, and modern platform design. In this session, he will share lessons from evolving systems from microservices to AI-agent-driven architectures.
Area of Expertise
Topics
When AI Agents Move to the Cloud: Infrastructure and Security in the Agentic Era
OpenClaw went from a weekend project to 200,000+ GitHub stars in weeks, and with it came developers spinning up cloud VMs to run autonomous AI agents 24/7. But cloud infrastructure was built for stateless, request-driven workloads. Agents are none of those things. They hold state, wake up on timers unprompted, inherit broad system permissions, and chain together API calls, file operations, and browser sessions in ways no one planned for.
This talk covers what breaks when agents hit cloud infrastructure. First, the architecture mismatch: why serverless and container platforms struggle with stateful, long-running, proactive workloads. Then the security surface, including supply chain attacks through unvetted skill repos, prompt injection as an infrastructure-level threat, and the gap in cloud IAM for non-human agent identities, grounded in real incidents and the OWASP Top 10 for Agentic Applications (2026).
Finally, what works. Reliability patterns from SRE: least-privilege scoping, container isolation, observability for agent workflows, and error budgets for destructive actions. You'll leave with a practical checklist for deploying agents on cloud safely.
PRO Session: From Microservices to AI Agents: Rethinking Cloud Architecture for the Intelligent Era
Microservices transformed cloud architectures over the last decade, enabling scalability, fault isolation, and team autonomy. Today, AI agents are redefining how modern systems are designed and operated, introducing dynamic orchestration, reasoning capabilities, and context-aware workflows.
In this session, we explore the evolution from microservices to AI-agent-driven architectures. We’ll discuss how AI agents integrate with cloud infrastructure, RAG pipelines, vector databases, and tool orchestration layers to build production-ready, intelligent systems.
Attendees will learn architectural patterns, operational best practices, reliability and security challenges, and how to design scalable AI-native systems. Real-world examples, diagrams, and practical guidance make this session highly valuable for students, engineers, and architects looking to understand the future of cloud and AI systems.
DeveloperWeek New York 2026 Sessionize Event
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