Loading…
AI DevSummit 2025 + DeveloperWeek Leadership 2025
Company: LLMs clear filter
Wednesday, May 28
 

1:00pm PDT

OPEN Session: From LLM to SLM - How and Where to Use Specialized Language Models
Wednesday May 28, 2025 1:00pm - 1:25pm PDT
Iddo Gino, Datawizz, CEO

LLMs have transformed many applications - putting advanced AI within any developers reach. This unlocked amazing progress - but also introduced a dependency on model providers and ballooning inference costs. This talk will discuss an alternative approach - fine tuning and deploying smaller, specialized language models to cut costs & improve performance. We'll discuss how to identify the right use cases for SLMs, evaluate their performance and deploy them effectively. 
Speakers
avatar for Iddo Gino

Iddo Gino

CEO, Datawizz
Part of Forbes 30 Under 30 list, he's a 2017 Thiel Fellow. Previously, he was a Co-organizer of Hacking Gen Y. Iddo has been programming since he was a kid and continues to contribute to open-source projects. Originally from Haifa, Israel, Iddo is based in San Francisco, CA.
Wednesday May 28, 2025 1:00pm - 1:25pm PDT
AI DevSummit Expo Stage
  AI DevSummit

3:00pm PDT

OPEN Session: The Road to Use OpenTelemetry for LLM Observability
Wednesday May 28, 2025 3:00pm - 3:25pm PDT
Nir Gazit, Traceloop, CEO

If 2024 is the year of LLMs, then 2025 will be the year for LLM Applications. As LLMs continue to integrate into various applications ranging from chatbots and search engines to creative writing aids, the need to monitor and comprehend their behaviors intensifies.

Observability plays a crucial role in this context. It involves the systematic collection and analysis of data to enhance LLM performance, identify and correct biases, troubleshoot issues, and ensure AI systems are both reliable and trustworthy.

In this discussion, we will explore the concept of LLM observability in depth, focusing on how OpenTelemetry can fit into the world of LLM observability . Additionally, we will talk about challenges around modeling of prompts, completions, events, semantic conventions, and basically our path with the llm-sem-conv working group.
Speakers
avatar for Nir Gazit

Nir Gazit

CEO, Traceloop
CEO @ traceloop; ex-chief architect @ Fiverr, ex-tech lead @ Google; OpenTelemetry contributor
Wednesday May 28, 2025 3:00pm - 3:25pm PDT
AI DevSummit Expo Stage
  AI DevSummit

4:00pm PDT

KEYNOTE (AI): Scale AI -- Ignore Previous Instructions: Embracing AI Red Teaming
Wednesday May 28, 2025 4:00pm - 4:50pm PDT
David Campbell, Scale AI, AI Risk Security Platform Lead

In this talk, we will explore the journey of Red Teaming from its origins to its transformation into AI Red Teaming, highlighting its pivotal role in shaping the future of Large Language Models (LLMs) and beyond. Drawing from my firsthand experiences developing and deploying the largest generative red teaming platform to date, I will share insightful antidotes and real-world examples. We will explore how adversarial red teaming fortifies AI applications at every layer—protecting platforms, businesses, and consumers. This includes safeguarding the external application interface, reinforcing LLM guardrails, and enhancing the security of the LLMs' internal algorithms. Join me as we uncover the critical importance of adversarial strategies in securing the AI landscape. 
Speakers
avatar for David Campbell

David Campbell

AI Risk Security Platform Lead, Scale AI
David Campbell is a seasoned technology leader with nearly 20 years of experience in Silicon Valley's startup ecosystem, now spearheading Responsible AI initiatives at Scale AI. As the Lead AI Risk Engineer, David has been pivotal in developing a cutting-edge AI Red Teaming platform... Read More →
Wednesday May 28, 2025 4:00pm - 4:50pm PDT
AI DevSummit Main Stage
 
Thursday, May 29
 

9:30am PDT

PRO Session: Building Production Ready, Intelligent Agentic Systems with Dapr Agents
Thursday May 29, 2025 9:30am - 9:55am PDT
Mark Fussell, Diagrid, CEO
Yaron Schneider, Diagrid, Co-Founder / CTO


As developers push the boundaries of AI-driven automation, the challenge of orchestrating and managing autonomous agents at scale becomes increasingly complex. Dapr Agents is an open-source framework that dramatically lowers the creation of production ready agentic systems, powered by the CNCF Dapr's (dapr.io) distributed application runtime, used by thousands of enterprises today in mission critical services. By combining LLM-driven reasoning with Dapr’s virtual actor model, pub/sub messaging, and stateful workflows, Dapr Agents enables developers to build intelligent, scalable, and fault-tolerant multi-agent systems.

This talk will provide a deep dive into Dapr Agents, demonstrating how it facilitates structured LLM interactions, tool selection, memory retention, and event-driven communication. We'll explore practical use cases, from task automation to collaborative agentic workflows, and discuss best practices for designing real world, robust agent-based architectures. We will also compare different agentic frameworks in use today and show how many of them only address a few of the requirements needed to go into production environments. Attendees will gain hands-on insights into implementing Dapr Agents for real-world applications, optimizing performance, and seamlessly integrating with existing cloud-native infrastructures.

If you're interested in building intelligent, scalable, and resilient agentic systems, this session will equip you with the knowledge to easily build these.
Speakers
avatar for Mark Fussell

Mark Fussell

CEO, Diagrid
CEO of Diagrid, a developer focused startup. Leader with proven track record of building innovative computing platforms, running large scale, cloud services, building OSS communities and starting new businesses.
avatar for Yaron Schneider

Yaron Schneider

Co-Founder / CTO, Diagrid
Yaron co-created the CNCF projects Dapr and KEDA while at Microsoft and led the engineering architecture for serverless container platforms that run at scale using open source technologies. Yaron is an avid lover of open source tech and distributed systems, and is a co-founder and... Read More →
Thursday May 29, 2025 9:30am - 9:55am PDT
AI DevSummit Main Stage

10:00am PDT

PRO Session: What’s Different About LLM Applications
Thursday May 29, 2025 10:00am - 10:25am PDT
Nuno Campos, LangChain, Founding Engineer

This talk identifies the three key things that make LLM applications different from previous software: latency, versatility and flakiness. LLMs are orders of magnitude slower than we were used to. The outputs of LLM apps are also more variable, and prone to mistakes. And LLM apps can be taken by users into domains we the creators didn’t necessarily program into them or expect. I’ll show how we can use these 3 qualities to our advantage, by learning to work with them, and so use them to build things that were simply impossible before. 
Speakers
avatar for Nuno Campos

Nuno Campos

Founding Engineer, LangChain
I'm a founding software engineer at LangChain, creator of LangGraph, the leading LLM agent framework, and co-author of the O’Reilly book Learning LangChain. Previously I was a maintainer of other popular open source packages, such as Enzyme, and have worked for tech startups for... Read More →
Thursday May 29, 2025 10:00am - 10:25am PDT
AI DevSummit Main Stage

2:00pm PDT

PRO Session: Decoding Enterprise AI for Devs: Choosing Between Private LLMs and Public Generative AI Services
Thursday May 29, 2025 2:00pm - 2:25pm PDT
Shomron Jacob, Iterate.aiHead of Applied Machine Learning & Platform

This AIDev Summit session will navigate an increasingly pivotal crossroads: the decision between investing in proprietary, custom-tailored Large Language Models (LLM) or capitalizing on the versatility and ease of public generative AI services.

The session will begin by demystifying the complexities of private LLMs. With domain-specific capabilities and enhanced data security, these models have faster customization and compliance with industry-specific regulations. Yet, they also pose challenges: a bigger investment, infrastructure requirements, and ongoing maintenance. These elements necessitate a thorough examination.

Next, the session will scrutinize public generative AI services, exploring the inherent benefits of these ready-to-use solutions. With their scalability, diverse applications, and lower upfront costs, they hold significant appeal. But they also come with their own set of considerations, such as data privacy, standardized performance, and reduced control over the model’s behavior.
With real-world examples, we will walk through how various organizations have approached this decision, the results they achieved, and the invaluable lessons learned.

The session will then go into a decision-making framework, with the purpose of enabling attendees to assess their options between private LLMs and public generative AI services more effectively.
Speakers
avatar for Shomron Jacob

Shomron Jacob

Head of Applied Machine Learning & Platform, Iterate.ai
Shomron Jacob is the Head of Applied Machine Learning & Platform at Iterate.ai. Shomron began his career as a software engineer but soon found himself learning ML/AI and switched his professional direction to follow it. He lives in Silicon Valley.
Thursday May 29, 2025 2:00pm - 2:25pm PDT
AI DevSummit Main Stage
 
Wednesday, June 4
 

1:00pm PDT

[Virtual] OPEN Session: From LLM to SLM - How and Where to Use Specialized Language Models
Wednesday June 4, 2025 1:00pm - 1:25pm PDT
Iddo Gino, Datawizz, CEO

LLMs have transformed many applications - putting advanced AI within any developers reach. This unlocked amazing progress - but also introduced a dependency on model providers and ballooning inference costs. This talk will discuss an alternative approach - fine tuning and deploying smaller, specialized language models to cut costs & improve performance. We'll discuss how to identify the right use cases for SLMs, evaluate their performance and deploy them effectively. 
Speakers
avatar for Iddo Gino

Iddo Gino

CEO, Datawizz
Part of Forbes 30 Under 30 list, he's a 2017 Thiel Fellow. Previously, he was a Co-organizer of Hacking Gen Y. Iddo has been programming since he was a kid and continues to contribute to open-source projects. Originally from Haifa, Israel, Iddo is based in San Francisco, CA.
Wednesday June 4, 2025 1:00pm - 1:25pm PDT
VIRTUAL AI DevSummit Expo Stage
  AI DevSummit

3:00pm PDT

[Virtual] OPEN Session: The Road to Use OpenTelemetry for LLM Observability
Wednesday June 4, 2025 3:00pm - 3:25pm PDT
Nir Gazit, Traceloop, CEO

If 2024 is the year of LLMs, then 2025 will be the year for LLM Applications. As LLMs continue to integrate into various applications ranging from chatbots and search engines to creative writing aids, the need to monitor and comprehend their behaviors intensifies.

Observability plays a crucial role in this context. It involves the systematic collection and analysis of data to enhance LLM performance, identify and correct biases, troubleshoot issues, and ensure AI systems are both reliable and trustworthy.

In this discussion, we will explore the concept of LLM observability in depth, focusing on how OpenTelemetry can fit into the world of LLM observability . Additionally, we will talk about challenges around modeling of prompts, completions, events, semantic conventions, and basically our path with the llm-sem-conv working group.
Speakers
avatar for Nir Gazit

Nir Gazit

CEO, Traceloop
CEO @ traceloop; ex-chief architect @ Fiverr, ex-tech lead @ Google; OpenTelemetry contributor
Wednesday June 4, 2025 3:00pm - 3:25pm PDT
VIRTUAL AI DevSummit Expo Stage
  AI DevSummit

4:00pm PDT

[Virtual] KEYNOTE (AI): Scale AI -- Ignore Previous Instructions: Embracing AI Red Teaming
Wednesday June 4, 2025 4:00pm - 4:50pm PDT
David Campbell, Scale AI, AI Risk Security Platform Lead

In this talk, we will explore the journey of Red Teaming from its origins to its transformation into AI Red Teaming, highlighting its pivotal role in shaping the future of Large Language Models (LLMs) and beyond. Drawing from my firsthand experiences developing and deploying the largest generative red teaming platform to date, I will share insightful antidotes and real-world examples. We will explore how adversarial red teaming fortifies AI applications at every layer—protecting platforms, businesses, and consumers. This includes safeguarding the external application interface, reinforcing LLM guardrails, and enhancing the security of the LLMs' internal algorithms. Join me as we uncover the critical importance of adversarial strategies in securing the AI landscape. 
Speakers
avatar for David Campbell

David Campbell

AI Risk Security Platform Lead, Scale AI
David Campbell is a seasoned technology leader with nearly 20 years of experience in Silicon Valley's startup ecosystem, now spearheading Responsible AI initiatives at Scale AI. As the Lead AI Risk Engineer, David has been pivotal in developing a cutting-edge AI Red Teaming platform... Read More →
Wednesday June 4, 2025 4:00pm - 4:50pm PDT
VIRTUAL AI DevSummit Main Stage
 
Thursday, June 5
 

9:30am PDT

[Virtual] PRO Session: Building Production Ready, Intelligent Agentic Systems with Dapr Agents
Thursday June 5, 2025 9:30am - 9:55am PDT
Mark Fussell, Diagrid, CEO
Yaron Schneider, Diagrid, Co-Founder / CTO


As developers push the boundaries of AI-driven automation, the challenge of orchestrating and managing autonomous agents at scale becomes increasingly complex. Dapr Agents is an open-source framework that dramatically lowers the creation of production ready agentic systems, powered by the CNCF Dapr's (dapr.io) distributed application runtime, used by thousands of enterprises today in mission critical services. By combining LLM-driven reasoning with Dapr’s virtual actor model, pub/sub messaging, and stateful workflows, Dapr Agents enables developers to build intelligent, scalable, and fault-tolerant multi-agent systems.

This talk will provide a deep dive into Dapr Agents, demonstrating how it facilitates structured LLM interactions, tool selection, memory retention, and event-driven communication. We'll explore practical use cases, from task automation to collaborative agentic workflows, and discuss best practices for designing real world, robust agent-based architectures. We will also compare different agentic frameworks in use today and show how many of them only address a few of the requirements needed to go into production environments. Attendees will gain hands-on insights into implementing Dapr Agents for real-world applications, optimizing performance, and seamlessly integrating with existing cloud-native infrastructures.

If you're interested in building intelligent, scalable, and resilient agentic systems, this session will equip you with the knowledge to easily build these.
Speakers
avatar for Mark Fussell

Mark Fussell

CEO, Diagrid
CEO of Diagrid, a developer focused startup. Leader with proven track record of building innovative computing platforms, running large scale, cloud services, building OSS communities and starting new businesses.
avatar for Yaron Schneider

Yaron Schneider

Co-Founder / CTO, Diagrid
Yaron co-created the CNCF projects Dapr and KEDA while at Microsoft and led the engineering architecture for serverless container platforms that run at scale using open source technologies. Yaron is an avid lover of open source tech and distributed systems, and is a co-founder and... Read More →
Thursday June 5, 2025 9:30am - 9:55am PDT
VIRTUAL AI DevSummit Main Stage

10:00am PDT

[Virtual] PRO Session: What’s Different About LLM Applications
Thursday June 5, 2025 10:00am - 10:25am PDT
Nuno Campos, LangChain, Founding Engineer

This talk identifies the three key things that make LLM applications different from previous software: latency, versatility and flakiness. LLMs are orders of magnitude slower than we were used to. The outputs of LLM apps are also more variable, and prone to mistakes. And LLM apps can be taken by users into domains we the creators didn’t necessarily program into them or expect. I’ll show how we can use these 3 qualities to our advantage, by learning to work with them, and so use them to build things that were simply impossible before. 
Speakers
avatar for Nuno Campos

Nuno Campos

Founding Engineer, LangChain
I'm a founding software engineer at LangChain, creator of LangGraph, the leading LLM agent framework, and co-author of the O’Reilly book Learning LangChain. Previously I was a maintainer of other popular open source packages, such as Enzyme, and have worked for tech startups for... Read More →
Thursday June 5, 2025 10:00am - 10:25am PDT
VIRTUAL AI DevSummit Main Stage

2:00pm PDT

[Virtual] PRO Session: Decoding Enterprise AI for Devs: Choosing Between Private LLMs and Public Generative AI Services
Thursday June 5, 2025 2:00pm - 2:25pm PDT
Shomron Jacob, Iterate.aiHead of Applied Machine Learning & Platform

This AIDev Summit session will navigate an increasingly pivotal crossroads: the decision between investing in proprietary, custom-tailored Large Language Models (LLM) or capitalizing on the versatility and ease of public generative AI services.

The session will begin by demystifying the complexities of private LLMs. With domain-specific capabilities and enhanced data security, these models have faster customization and compliance with industry-specific regulations. Yet, they also pose challenges: a bigger investment, infrastructure requirements, and ongoing maintenance. These elements necessitate a thorough examination.

Next, the session will scrutinize public generative AI services, exploring the inherent benefits of these ready-to-use solutions. With their scalability, diverse applications, and lower upfront costs, they hold significant appeal. But they also come with their own set of considerations, such as data privacy, standardized performance, and reduced control over the model’s behavior.
With real-world examples, we will walk through how various organizations have approached this decision, the results they achieved, and the invaluable lessons learned.

The session will then go into a decision-making framework, with the purpose of enabling attendees to assess their options between private LLMs and public generative AI services more effectively.
Speakers
avatar for Shomron Jacob

Shomron Jacob

Head of Applied Machine Learning & Platform, Iterate.ai
Shomron Jacob is the Head of Applied Machine Learning & Platform at Iterate.ai. Shomron began his career as a software engineer but soon found himself learning ML/AI and switched his professional direction to follow it. He lives in Silicon Valley.
Thursday June 5, 2025 2:00pm - 2:25pm PDT
VIRTUAL AI DevSummit Main Stage
 

Share Modal

Share this link via

Or copy link

Filter sessions
Apply filters to sessions.