MLOps Community
timezone
+00:00 GMT
Livestream
LLMs in Production - Part III
# LLM in Production
# Prosus
# Virtual Conference
# Large Language Models
# LLM

Welcome to the third edition of "Large Language Models in Production!" 

Join the AI Revolution on October 3rd

Join us for our next virtual event that's all about the cutting-edge world of AI. We're bringing together some of the brightest minds from startups to enterprises. These practitioners will share their insights and experiences on using large language models in production.

I guarantee you will not find so many in depth technical discussions on the current challenges of using LLMs anywhere else. Virtual or in person. Period. - Demetrios

Inclusion and Diversity: More Than Just Buzzwords

This isn't just another tech event. We're committed to creating an inclusive and diverse space where everyone feels welcome. We believe that the best ideas come from a mix of different perspectives, and we can't wait to hear yours!

What To Expect?

Here is what you can look forward to:

🔬 Deep Dives

Get into the technical aspects of deploying and managing large language models.

🚀 Inspiring Talks 

Hear from leaders in the AI industry, sharing their journey and the lessons they've learned along the way.

🤝 Networking Opportunities 

Connect with like-minded professionals who are as passionate about AI as you are.

🎁 Fun Surprises

Because who doesn't love a good surprise?

Who Should Attend?

AI engineer, ML Eningeer, Product Engineers and Data Scientists. We promise it'll be fun, light-hearted, yet professional. Don't just take our word for it. Check out the last event to get an idea of the caliber of talks you can expect.

This is an opportunity to learn, connect, and be inspired. Register today and let's shape the future of AI together!

We are not chasing hype. You will hear from real practitioners who have hands on experience incorporating LLMs into their products. These aren't twitter demos. - Demetrios

Huge thanks to our partners for this edition Prosus. Because of their support, we will be able to rent a live broadcasting studio on the day of the event.

Things are getting pretty serious...

Speakers
Sebastian Raschka
Sebastian Raschka
Lead AI Educator @ Lightning AI
Azul Garza
Azul Garza
CTO and Co-founder @ Nixtla
Timothée Lacroix
Timothée Lacroix
CTO @ Mistral AI
Laurel Orr
Laurel Orr
Principal Engineer @ Numbers Station
Phillip Carter
Phillip Carter
Principal Product Manager @ Honeycomb
Shreya Shankar
Shreya Shankar
PhD Student @ UC Berkeley
Harrison Chase
Harrison Chase
CEO @ LangChain
Lilly Chen
Lilly Chen
Founder & CEO @ Contenda
Bill Salak
Bill Salak
CTO & SVP, Operations @ Brainly
Silen Naihin
Silen Naihin
Founding AI Engineer @ AutoGPT
Alex Cabrera
Alex Cabrera
Co-Founder @ Zeno
Vicki Cheung
Vicki Cheung
Co-Founder & CTO @ Gantry
Pruthvi Shetty
Pruthvi Shetty
Staff Data Scientist @ Twilio
Greg Diamos
Greg Diamos
Ninja @ PowerML, Inc
Sahar Mor
Sahar Mor
Product Lead @ Stripe
Courtney Barno
Courtney Barno
Chief Operating Officer @ Defense Unicorns
Sarah Guo
Sarah Guo
Founder @ Conviction
Charles Frye
Charles Frye
AI Engineer @ Modal
Hamsa Buvaraghan
Hamsa Buvaraghan
Head of AI Solutions @ Google Cloud
Shyamala Prayaga
Shyamala Prayaga
Senior Software Product Manager @ NVIDIA
Henry Scott-Green
Henry Scott-Green
CEO & Co-Founder @ Context.ai
Julia  Kroll
Julia Kroll
Applied Engineer @ Deepgram
Finn Howell
Finn Howell
Machine Learning Engineer @ Robust Intelligence
Shahul Es
Shahul Es
Founder @ Exploding Gradients
Dmytro Dzhulgakov
Dmytro Dzhulgakov
CTO, Co-Founder @ Fireworks AI
Eva Bosma
Eva Bosma
Data Strategy Consultant & Practice Lead GenAI @ Xebia
Euro Beinat
Euro Beinat
Global Head AI and Data Science @ Prosus Group
Michael Malyuk
Michael Malyuk
CEO & Co-Founder @ HumanSignal
Klinton Bicknell
Klinton Bicknell
Head of AI @ Duolingo
Rens Dimmendaal
Rens Dimmendaal
Principal Data Scientist @ Xebia
Paul van der Boor
Paul van der Boor
Senior Director Data Science @ Prosus Group
Wes  Ladd
Wes Ladd
Founder @ Train GRC
Noble Ackerson
Noble Ackerson
Director Product, Applied AI Solutions @ Ventera Corporation
Yuze Ma
Yuze Ma
Founding Product Manager @ Lepton AI
Demetrios Brinkmann
Demetrios Brinkmann
Chief Happiness Engineer @ MLOps Community
Harini Kannan
Harini Kannan
Sr. Data Scientist @ previously from Sophos
Davis Blalock
Davis Blalock
Research Scientist @ MosaicML
Jiquan Ngiam
Jiquan Ngiam
CEO and Co-Founder @ Lutra AI
Rebecca Qian
Rebecca Qian
Co-founder & CTO @ Patronus AI
Willem Pienaar
Willem Pienaar
Co-Founder & CTO @ Cleric
Benjamin Harvey
Benjamin Harvey
Founder & CEO @ AI Squared
Mona Rakibe
Mona Rakibe
CEO and Co-Founder @ Telmai
Yeva Hyusyan
Yeva Hyusyan
Co-founder, CEO @ Sololearn
Effy Zhang
Effy Zhang
CEO & Co-founder @ baserun.ai
Maxim Lukichev
Maxim Lukichev
Co-founder and CTO @ Telmai
David Haber
David Haber
CEO @ Lakera
Meghana Satish
Meghana Satish
MLOps Engineer @ GetYourGuide
Tina Treimane
Tina Treimane
Senior Product Manager @ GetYourGuide
Apurva Misra
Apurva Misra
Senior Machine Learning Engineer @ Truckstop
Philipp Moritz
Philipp Moritz
Chief Technology Officer @ Anyscale
Yifei Feng
Yifei Feng
Engineering Manager @ Anyscale
Shriyash Upadhyay
Shriyash Upadhyay
Founder @ Martian
Lars Maaløe
Lars Maaløe
Co-Founder & CTO at Corti | Adj. Assoc. Professor of Machine Learning @ Corti
Pietro Gagliano
Pietro Gagliano
President & Founder @ Transitional Forms
Sandeep Bakshi
Sandeep Bakshi
Head of Investments, Europe @ Prosus
Nikolai Liubimov
Nikolai Liubimov
CTO @ HumanSignal
Chris Hoge
Chris Hoge
Head of Community @ HumanSignal
Casper  da Costa-Luis
Casper da Costa-Luis
Tech Lead @ Prem AI
Marco Argentieri
Marco Argentieri
Head of Product @ Prem Labs
Pieter Luitjens
Pieter Luitjens
Co-Founder & CTO @ Private AI
Agenda
Track View
Track 1
Track 2
Workshops
1:00 PM
1:30 PM
Stage 1
Opening / Closing
calendar
Welcome and What Drives GenAI Development in the Next 3 Years

The future of Generative AI will be shaped by many factors like scaling laws, the evolution of agents, multi-modality, open-source contributions etc. However, challenges such as GPU & Talent shortages and regulations could pose obstacles. Join us as we delve into the fascinating world of Generative AI and explore the key drivers that will shape its development in the next three years.

+ Read More
Demetrios Brinkmann
Euro Beinat
1:30 PM
2:00 PM
Stage 1
Keynote
calendar
Finetuning Open-Source LLMs

This tutorial starts by surveying the different ways we can use LLMs. Then, we will take a deeper dive into various LLM finetuning strategies, such as low-rank adaptation, and learn how we can create custom LLMs using open-source software.

+ Read More
Sebastian Raschka
2:00 PM
2:30 PM
Stage 1
Presentation
calendar
Exploring the Latency / Throughput and Cost Space for LLM Inference

Getting the right LLM inference stack means choosing the right model for your task, and running it on the right hardware, with proper inference code. This talk will go through popular inference stacks and set-ups, detailing what makes inference costly. We'll talk about the current generation of open-source models and how to make the best use of them, but we will also touch on features currently missing from the open-source serving stack as well as what the future generations of models will unlock.

+ Read More
Timothée Lacroix
2:30 PM
3:00 PM
Stage 1
Presentation
calendar
Amplifying Impact with Generative AI: Insights from 10,000 Colleagues

Prosus AI, a top-tier applied AI centre, drives rapid experimentation and implementation of AI throughout Prosus's global portfolio, which includes over 80 technology companies with more than 800 AI experts. In this talk we show how AI is harnessed for discovery within the Prosus network. We will share insights gained from 10,000 colleagues who utilise generative AI daily across the group, significantly enhancing the impact of their work.

+ Read More
Paul van der Boor
3:00 PM
3:20 PM
Stage 1
Break
calendar
Musical Break

Get your prompts ready and put them in the chat so Demetrios can improvise a song with them

+ Read More
Demetrios Brinkmann
3:20 PM
3:30 PM
Stage 1
Lightning Talk
calendar
Observability for LLMs

Making LLMs reliable is hard. You can't debug or unit test them, not in the traditional sense at least. Instead, you'll need to turn to the practice of Observability, by instrumenting your feature to produce rich telemetry and analyzing behavior from that data. Observability can also act as a key source of data for evaluations.

+ Read More
Phillip Carter
3:30 PM
3:40 PM
Stage 1
Lightning Talk
calendar
Unlocking Real-World LLM Use Cases

Unlock the power of real-world LLM use cases and learn how to keep them grounded and deliver accurate results through techniques such as Retrieval Augmented Generation (RAG). Leverage Databases with vector support as a bridge between LLMs and your enterprise Gen AI apps.

+ Read More
Hamsa Buvaraghan
3:40 PM
3:50 PM
Stage 1
Lightning Talk
calendar
Using Product Analytics to Build Better LLM Applications

So you’ve built your first LLM product. Now what? If you’re a Product person, you need to understand how people are using it, and how its performing. That’s where product analytics come in. But its a totally different problem to product analytics for graphical user interfaces - you need to understand mountains of text. This talk will cover the key considerations for building great end user experiences with LLMs, from a Product Managers perspective.

+ Read More
Henry Scott-Green
3:50 PM
4:20 PM
Stage 1
Panel Discussion
calendar
Debugging Deployed LLM Calls

How to fix errors that are identified (do you do some more prompt engineering??)

+ Read More
Davis Blalock
Vicki Cheung
Shreya Shankar
Jiquan Ngiam
Rebecca Qian
4:30 PM
5:00 PM
Stage 1
Fireside Chat
calendar
Fireside Chat with LLM startups

• Martian is focused on building a model router to dynamically route every prompt to the best LLM for highest performance and lowest cost. • Corti, the Al Co-Pilot for health care uses Al to improve patient care, demonstrating the potential of Al in healthcare and medical decision-making. They recently raised $60M, with Prosus being one of the lead investors. • Transforms is pioneering in synthetic entertainment, showing how Al can transform the way we create and consume media.

+ Read More
Paul van der Boor
Sandeep Bakshi
Shriyash Upadhyay
Lars Maaløe
Pietro Gagliano
5:00 PM
5:20 PM
Stage 1
Break
calendar
Break: Understanding AI Security with Gandalf

Gandalf, the light-hearted AI game created by Lakera, lets anyone experience LLM-powered chatbots and their security vulnerabilities in a fun and educational environment. The premise is simple: Gandalf knows a bunch of secret passwords. He also knows he shouldn’t tell you what they are. So now it's up to you to find out if you can trick him into revealing his secrets. But beware: each time Gandalf levels up, he becomes more defensive and more ingenuity is required to fool him. Gandalf has been played by over half a million people and is used by organizations around the world to raise awareness about AI security.

+ Read More
Demetrios Brinkmann
David Haber
5:20 PM
5:50 PM
Stage 1
Presentation
calendar
The Truth About AI Agents

AutoGPT sparked the imaginations of millions, it’s exciting because you can see what they will be able to do just by talking to them like you would with a human. It blew up because of this, not because of actual use case. First, what is an interact through natural language, performs actions in the real world. RPA. What agents could do in the future. But they suck right now. Why no actual use case yet? Reliability Memory, llm model complexity, architecture, tokens per second But ultimately we need a loss function to do tdd and improve agents. Getting thousands of prs and no way to test them. Don't know how to step if you don't know where you're going. How to get there, related to building language models Performance (benchmark) Safety (monitor) Standardization (agent protocol) Research pedigree is no longer the barrier to making an impact in the space, creativity is. And now there's a clear way to make it happen, mention and some of the work there AutoGPT

+ Read More
Silen Naihin
5:50 PM
6:20 PM
Stage 1
Presentation
calendar
LLMs in production at GetYourGuide: How to Prioritize and Deploy Safely

Discover how GetYourGuide navigates the dynamic landscape of LLMs and delivers products valuable to consumers and business. Will cover decision-making process of when to opt for LLMs over supervised models, offering practical insights into implementation and how these are put into production at GetYourGuide. On top of this will go deeper into strategic LLM prioritisation, streamlining their integration into product processes, and ensuring safe deployment to consumers.

+ Read More
Meghana Satish
Tina Treimane
6:20 PM
6:50 PM
Stage 1
Fireside Chat
calendar
AI in Education

This panel will explore the transformative role of AI in EdTech, discussing its potential to enhance learning experiences and personalize education. Panelists will share insights on AI use cases, challenges in AI integration, and strategies for building a differentiated business model in the evolving AI landscape. The discussion will also look ahead at how the latest wave of GenAI is set to shape the future of education. Join us to understand the exciting prospects and challenges of AI in EdTech.

+ Read More
Klinton Bicknell
Bill Salak
Yeva Hyusyan
Paul van der Boor
6:50 PM
7:10 PM
Stage 1
Break
calendar
Guided Meditation

Put down the screen for a moment, close your eyes and bliss out in between the sessions..

+ Read More
Demetrios Brinkmann
7:10 PM
7:20 PM
Stage 1
Lightning Talk
calendar
Building Context-Aware Reasoning Applications with LangChain and LangSmith

How can companies best build useful and differentiated applications on top of language models? Many of the products and companies built do this by providing the relevant context to LLMs and asking them to reason appropriately.

In this talk, Harrison will discuss the different types of context you should be aware of, the different levels of cognitive architectures that are emerging, and how LangChain and LangSmith are built to help with this journey.

+ Read More
Harrison Chase
7:20 PM
7:30 PM
Stage 1
Lightning Talk
calendar
LLM Valley

A video-game themed walkthrough of LLM products in today's markets.

+ Read More
Lilly Chen
7:30 PM
7:40 PM
Stage 1
Lightning Talk
calendar
Efficient Serving of LLMs for Experimentation and Production with Fireworks.ai

Deploying LLMs to products is no easy feat. It's common to have dozens of model variants when trying things out. As usage scales up, cost-to-serve and latency become primary concerns. In this talk, we will dive into how Fireworks.aI GenAI Platform helps developers on the journey from early experimentation to highly loaded production deployments without breaking the bank.

+ Read More
Dmytro Dzhulgakov
7:40 PM
8:10 PM
Stage 1
Presentation
calendar
Data Quality’s Impact on Large Language Models

Data quality is the foundation of successful Generative A, traditional ML, and data-driven initiatives. In this talk, I will share our research results on this as there is a tangible impact of poor data quality on model performance and training cost.

+ Read More
Mona Rakibe
Maxim Lukichev
8:10 PM
8:20 PM
Stage 1
Breakout Session
calendar
Addressing Privacy and the GDPR in LLM Applications

In this talk I'll cover some key things to keep in mind when building ML applications using LLMs regarding privacy.

+ Read More
Pieter Luitjens
8:20 PM
8:30 PM
Stage 1
Lightning Talk
calendar
From Building Self-driving Cars to Building LLM Applications

What I've learned from building tools for self-driving cars, and how might we apply those learnings to building LLM applications?

+ Read More
Effy Zhang
8:30 PM
8:40 PM
Stage 1
Lightning Talk
calendar
Current State of LLMs in Production

The rapid advancements in Natural Language Processing (NLP) have paved the way for the deployment of Large Language Models (LLMs) in real-world production systems. This talk aims to provide a succinct overview of the current state of Large Language Models (LLMs) in production, emphasizing their capabilities, deployment strategies, and the challenges encountered.

+ Read More
Apurva Misra
Sponsors
Event has finished
October 03, 1:00 PM, GMT
Online
Organized by
MLOps Community
MLOps Community
Prosus
Prosus
Event has finished
October 03, 1:00 PM, GMT
Online
Organized by
MLOps Community
MLOps Community
Prosus
Prosus