SF Bay ACM Chapter

LOCATION ADDRESS (Hybrid, in person or by zoom, you choose)
Valley Research Park
319 North Bernardo Avenue
Mountain View, CA CA 93043
If you want to join remotely, you can submit questions via Zoom Q&A. The zoom link:
https://acm-org.zoom.us/j/
Join via YouTube:
https://youtube.com/live/sJ38lsfLfeU

AGENDA
6:30 Door opens, SFBAY ACM 68 anniversary Cake and networking (we invite honor system contributions)
7:00 SFBay ACM 2026 Slate of board members and annual election, upcoming events.
7:15 Dr. Tom Coughlin :"The IEEE Mass Storage Roadmap 2026 Update"
8:25- 8:40 finish, depending on Q&A

Join SF Bay ACM Chapter for an insightful discussion on:

Abstract
A group of experts recently completed a roadmap for all types of digital storage technology out 15 years into the future. This includes NAND flash and new non-volatile memories, hard disk drives, magnetic tape, optical storage and DNA storage. Come to this talk to get a glimpse of the future of something that people can’t get enough of, digital storage technology.

Speaker Bio:
Tom Coughlin, President, Coughlin Associates is a digital storage analyst and business/ technology consultant. He has over 40 years in the data storage industry with engineering and senior management positions. Coughlin Associates consults, publishes books and market and technology reports and puts on digital storage and memory-oriented events. He is a regular contributor for forbes.com and M&E organization websites. He is an IEEE Fellow, an ACM Senior Member, 2024 IEEE President, Past-President IEEE-USA, Past Director IEEE Region 6 and Past Chair Santa Clara Valley IEEE Section, and is also active with SNIA, SMPTE and CNSV. For more information on Tom Coughlin go to www.tomcoughlin.com.

---

Valley Research Park is a coworking research campus of 104,000 square feet hosting 30+ life science and technology companies. VRP has over 100 dry labs, wet labs, and high power labs sized from 125-15,000 square feet. VRP manages all of the traditional office elements: break rooms, conference rooms, outdoor dining spaces, and recreational spaces.

As a plug-and-play lab space, once companies have secured their next milestone and are ready to expand, VRP has 100+ labs ready to expand into.
https://www.valleyresearchpark.com/

If you want to join discussion remotely, you can submit questions via Zoom Q&A. The zoom link:
https://acm-org.zoom.us/j/94932457090?pwd=SzCaJbWEJpzEpJl7wYa1aSrHa8G15r.1
Join via YouTube:
https://youtube.com/watch?v=t15Ca-KblbE

AGENDA
6:30 pre-sign in to test and chat
7:00 SFBayACM upcoming events, introduce the speaker
7:15 speaker presentation starts
8:15 - 8:30 finish, depending on Q&A

Join SF Bay ACM Chapter for an insightful discussion in person at VRP

Description:
Search systems are evolving rapidly, powered by advances in deep learning, embeddings, and now large language models. This talk offers a 360° view of modern search architectures: from query understanding and candidate generation to pre-ranking, ranking, and re-ranking. We’ll explore how hybrid retrieval (sparse + dense), multi-task learning, and LLM-assisted query understanding are redefining search quality and personalization. Attendees will gain a systems-level understanding of how each layer contributes to relevance, diversity, and user satisfaction, and where to focus next for scalable innovation.

Audience:
AI practitioners interested in understanding how modern search systems work end-to-end. Also suitable for product engineers and researchers. Beginner to intermediate level: designed for attendees familiar with basic ML and data concepts, but not requiring deep expertise in search or ranking systems.

Speaker Bio:
Gauri Sarode is a Senior Machine Learning Engineer at Doordash, where she builds large-scale personalization and search systems that shape the customer discovery experience. With an M.S. in Computer Science from New York University, Gauri combines academic depth with real-world production experience. She holds multiple certifications in Generative AI and Retrieval-Augmented Generation.
LinkedIn: https://www.linkedin.com/in/gaurisarode/
---

Valley Research Park is a coworking research campus of 104,000 square feet hosting 60+ life science and technology companies. VRP has over 100 dry labs, wet labs, and high power labs sized from 125-15,000 square feet. VRP manages all of the traditional office elements: break rooms, conference rooms, outdoor dining spaces, and recreational spaces.

As a plug-and-play lab space, once companies have secured their next milestone and are ready to expand, VRP has 100+ labs ready to expand into.
https://www.valleyresearchpark.com/

If you want to join remotely, you can submit questions via Zoom Q&A. The zoom link:
Zoom (updated 6:55 pm)
Join via YouTube:
https://www.youtube.com/watch?v=pO72Hb30fKw

AGENDA
6:30 Door opens, food and networking (we invite honor system contributions)
7:00 SFBayACM upcoming events, introduce the speaker
7:15 Speaker presents.
8:30 - 8:45 finish, depending on Q&A

Join SF Bay ACM Chapter for an insightful discussion on:

### Abstract & Overview

An agent is simple: Prompt + Tools + Model + Boilerplate. The first three are where product teams create value. The last one—state management, history compression, streaming, cancellation, tracing, memory, persistence—is 80% of the code but 0% of the differentiation.
At ThoughtSpot, we built an Agent Platform that draws a hard line between agent logic and agent infrastructure, letting product teams ship customer-facing agents faster by owning only what matters: their prompts and their tools.
This talk covers the infrastructure patterns behind that separation:
State management across tool calls. Stateless tools (state on the agent, passed as arguments) give you testability and let the LLM reason about state. Stateful tools (state in the tool service) avoid serialization overhead. I'll walk through flow diagrams, show how we propagate state via tool response metadata, and discuss when each pattern fits.
Configuration-driven agent definitions. Agents defined entirely through config—templated prompts, tool endpoints, sub-agent rules, compression strategies. Teams ship agents without writing orchestration code.
Inter-agent communication. Two patterns: agents-as-tools (sub-agent called like any tool, returns structured output) and agent handoff (full conversation transfer). The platform handles routing and context—teams just declare delegation rules.
Shared memory across agents. Memory in the platform, not individual agents, means knowledge accumulates across agent boundaries. Tiered scoping (tenant, org, user) with retrieval that surfaces relevant context regardless of which agent captured it.
Tool protocol design. MCP as the base, with patterns layered on top: cancellation semantics, progress streaming, context variable propagation, and adapters for existing services.
Building for customer-facing scale adds constraints—high concurrency, encryption, tenant isolation, auditability—that shaped our API design throughout.
Takeaways:

• Mental model for separating agent value from infrastructure
• State patterns: agent-side vs. tool-side tradeoffs
• Inter-agent communication: tools vs. handoff
• Shared memory architecture across agent boundaries
• MCP extensions for production systems.

Speaker Bio
Ashish Shubham is Fellow/Vice President of Engineering at ThoughtSpot, where he leads the architecture of enterprise-scale AI and embedded analytics platforms used by Fortune 500 organizations. He is the author of Architecting AI Data Systems and an inventor on multiple U.S. patents in natural-language-to-SQL, generative AI interfaces, and intelligent analytics. Ashish is an IEEE Senior Member and an active reviewer and committee contributor for leading IEEE and ACM conferences and workshops. His work bridges academic research and real-world deployment, with a focus on building scalable, trustworthy, and developer-centric AI systems for production environments.
https://linkedin.com/in/ashubham

---
Valley Research Park is a coworking research campus of 104,000 square feet hosting 60+ life science and technology companies. VRP has over 100 dry labs, wet labs, and high power labs sized from 125-15,000 square feet. VRP manages all of the traditional office elements: break rooms, conference rooms, outdoor dining spaces, and recreational spaces.

As a plug-and-play lab space, once companies have secured their next milestone and are ready to expand, VRP has 100+ labs ready to expand into.
https://www.valleyresearchpark.com/

If you want to join discussion remotely, you can submit questions via Zoom Q&A. The zoom link:
https://acm-org.zoom.us/j/94932457090?pwd=SzCaJbWEJpzEpJl7wYa1aSrHa8G15r.1
Join via YouTube:
https://youtube.com/watch?v=t15Ca-KblbE

AGENDA
6:30 pre-sign in to test and chat
7:00 SFBayACM upcoming events, introduce the speaker
7:15 speaker presentation starts
8:15 - 8:30 finish, depending on Q&A

Join SF Bay ACM Chapter for an insightful discussion in person at VRP

Abstract:
As modern AI-powered and real-time applications grow, they increasingly rely on complex event-driven infrastructure. This session explores practical lessons learned from operating large-scale messaging and distributed systems in production. We will dive into the critical trade-offs regarding reliability, scalability, and observability in asynchronous environments, and discuss how architectural decisions compound when systems reach global scale.

Speaker Bio:
Ajinkya Kher is an Engineering Manager at Meta and former Principal Engineering Manager at Microsoft with over 15 years of experience building and leading large-scale distributed systems. Throughout his career, he has worked on highly scaled platforms, including real-time messaging platform powering Microsoft Teams & AI-powered experiences supporting hundreds of millions of users worldwide. At Meta, he leads engineering teams building youth-focused experiences across Facebook and Messenger, with a focus on trust and safety.

Ajinkya is currently authoring a book with Manning Publications on designing and operating event-driven systems in production. He previously authored a book on high-performance TypeScript programming and enjoys sharing practical lessons from building software at scale. Beyond his day-to-day work, he enjoys mentoring engineers and supporting technology and innovation programs that help develop future engineering leaders.
LinkedIn: https://www.linkedin.com/in/ajinkyakher
---

Valley Research Park is a coworking research campus of 104,000 square feet hosting 60+ life science and technology companies. VRP has over 100 dry labs, wet labs, and high power labs sized from 125-15,000 square feet. VRP manages all of the traditional office elements: break rooms, conference rooms, outdoor dining spaces, and recreational spaces.

As a plug-and-play lab space, once companies have secured their next milestone and are ready to expand, VRP has 100+ labs ready to expand into.
https://www.valleyresearchpark.com/