Speaker

Sohil Shah

Sohil Shah

Staff Software Engineer - Agentic AI @PayPal | Ex-TikTok, Ex-JPMC

San Jose, California, United States

Actions

Sohil Shah is a Staff Software Engineer at PayPal, where he leads the development of the Agentic AI platform for operational intelligence across the company. Previously, he served as a Tech Lead at Bytedance/TikTok, where he has played a key Lead role on Project Texas, and before this held a Vice President role at JPMorgan Chase, where he spent the majority of his time architecting global complex Payment systems.

Area of Expertise

  • Information & Communications Technology
  • Media & Information

Topics

  • Artificial Intelligence (AI)
  • Artificial Intelligence (AI) and Machine Learning
  • Agentic AI
  • Software Design

Autonomous Incident Lifecycle Management using AI Agents

SRE teams at PayPal have developed a multi-agent orchestration framework to autonomously manage the full incident lifecycle starting from detection and intelligent triage to stakeholder communication, automated mitigation, and post-incident RCA. By leveraging agentic AI, the platform reduces end-to-end incident MTTR from ~45 minutes to under 5 minutes.

In this session, we’ll explore the architecture behind the system. We will also talk about our frameworks used including how agents collaborate, share persistent memory, generate memories, manage context and safely execute remediation workflows in production environments including HITL (human-in-the-loop).

Attendees will have a clear understanding of how to leverage AI Agents in SRE space and drive faster incident resolution. They will also learn how PayPal reduced in operational cost per incident and scale incident triage beyond priority incidents to other indicators and stop lower priority issues before that start introducing financial impact.

Leveraging A2A Protocol to build framework agnostic Multi-Agent system

With the growing number of Agentic AI Frameworks and a constantly evolving landscape of AI Agents, ensuring interoperability between agents built on different ecosystems has become a critical challenge. The A2A (Agent-to-Agent) protocol addresses this need by enabling standardized communication and coordination across diverse AI agents.
In this session, we will explore what A2A is, how it works, and how it compares to MCP. We’ll break down the A2A architecture and demonstrate how agents can seamlessly communicate and collaborate using this protocol. Attendees will gain a practical understanding through an end-to-end demo built on A2A.
We’ll also examine real-world use cases and discuss how A2A can be leveraged to build scalable, interoperable agent systems in production environments.

Sohil Shah

Staff Software Engineer - Agentic AI @PayPal | Ex-TikTok, Ex-JPMC

San Jose, California, United States

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