The Fast Path to Developing with LLMs

On Demand

Summary

Learn practical methods for designing and implementing LLM-powered systems on real-world business data using popular, ready-to-go LLM APIs—no specialized hardware, model training, or tricky deployment required. We'll show techniques for engineering effective inputs to the models (“prompts”) and how to combine LLMs with other systems, including business databases, with toolkits workflow frameworks like LangChain. Join us and learn how to build LLM systems to generate tangible business results..

Speaker

David Taubenheim

Senior Solutions Architect
NVIDIA

David Taubenheim is a Senior Solutions Engineer in NVIDIA's Developer Programs organization, driving AI approaches to business challenges. Prior to his work at NVIDIA, David directed a program area of engineers, scientists, and technical managers supporting US Government sponsors through specialized technology programs and emergent initiatives at the Johns Hopkins University Applied Physics Laboratory (APL). Earlier, David's work at Motorola focused on the design of bespoke digital signal processing systems using custom software defined radio platforms, earning him the company's Distinguished Innovator Award. In 2018, David received the Engineer of the Year Award by the National Organization of Gay and Lesbian Scientists and Technical Professionals for his contributions to national security technologies. He has a Master of Science in Electrical Engineering and has been granted 17 patents for a variety of technical inventions.

Tailoring LLMs to Your Use Case

On Demand

Summary

Push LLMs beyond the quality limits of off-the-shelf models and APIs by customizing them for domain-specific applications. We'll discuss strategies for preparing datasets and showcase gains from different forms of customization using practical, real-world examples. Join us and learn about model tuning techniques applicable for both API-based and self-managed LLMs.

Speaker

Christopher Pang

Senior Solutions Engineer
NVIDIA

Chris Pang is a Senior Solutions Engineer in NVIDIA's Developer Programs organization. Before joining NVIDIA, Chris worked in baseball analytics. He was a member of the front offices of the New York Mets and New York Yankees, where he split time between working on statistical models for player evaluation and full-stack development of internal web applications. Chris studied Applied Physics at Yale University.

Large Language Models and Generative AI for Life Sciences

On Demand

Summary

In this session, we will explore foundational AI models in biology, as well as practical protein engineering and design applications supported by real-world examples. We will discuss recent biology breakthroughs and apply that to how you can use LLMs to predict protein structure and function and encode protein data computationally. Attendees will learn techniques for how to use NVIDIA BioNeMo, a generative AI platform for drug discovery, to simplify and accelerate training of models on their own data, ensuring easy and scalable deployment of models for drug discovery applications.

Speakers

Chris Dallago

Senior Solutions Architect
NVIDIA

Chris is a computer scientist turned bioinformatician with a passion for systematically modelling biological mechanisms through machine learning. His path towards reaching this goal led him to contribute and push the community of learned protein sequence representations in order to find new, principled ways to describe biological entities. Bio-sequence representation learning, for instance through transformer models, is today an established field in bioinformatics with flourishing frameworks - even by NVIDIA - and impactful research applications, like the prediction of protein 3D structure from just an input sequence. However, Chris remains focused on trying to address problems for which data and intuition remain scarce, for instance those allowing to design new proteins with therapeutic or industrial use.

Dr. Chelsea Sumner, PharmD, RPh

NALA Healthcare AI Startups Lead
NVIDIA

Chelsea Sumner leads healthcare AI startups in North and Latin America at NVIDIA, managing more than 450 healthcare startups in the digital health, medical instrument, medical imaging, genomics, and drug discovery segments. Before this, she was a brand manager for Eli Lilly and Company and worked in a variety of clinical pharmacy settings, including CVS, for over six years. Chelsea graduated from the University of North Carolina at Chapel Hill Eshelman School of Pharmacy with a Doctor of Pharmacy degree and holds a bachelor’s in clinical research from Campbell University in North Carolina. In her free time, she enjoys trying new food when traveling, learning new exercises when working out, and reading.

Running Your Own LLM

On Demand

Summary

Optimizing and deploying LLMs on self-managed hardware—whether in the cloud or on premises–can produce tangible efficiency, data governance, and cost improvements for organizations operating at scale. We'll discuss open, commercially licensed LLMs that run on commonly available hardware and show how to use optimizers to get both lower-latency and higher-throughput inference to reduce compute needs. Join us and learn how to scale up self-managed LLMs to accommodate unique business and application requirements.

Speaker

Emily Apsey

Senior Technical Marketing Engineering Manager
NVIDIA

Emily Apsey is a Manager of NVIDIA Technical Marketing Engineers. She works closely with both internal and external stakeholders, on initiative such as marketing, engineering, and business development. Emily is just as happy talking to and teaching others, as she is heads down leading and using NVIDIA AI-Ready Enterprise technolog

Reinventing the Complete Cybersecurity Stack With AI Language Models

On Demand

Summary

Cybersecurity is a data problem, and one of the most effective ways of contextualizing data is via natural language. With the advancement of Large Language Models (LLMs) and accelerated compute capabilities, we can represent security data in ways that expand our detection and data generation techniques. Here we discuss advancements in LLMs, including how to leverage throughout the cybersecurity stack from copilots to synthetic data generation.

Speaker

Bartley Richardson, PhD

Director, Cybersecurity Engineering
NVIDIA

Bartley Richardson is director of cybersecurity engineering at NVIDIA and leads a cross-discipline team researching GPU-accelerated machine learning and deep learning techniques and creating new frameworks for cybersecurity. His interests include natural language processing and sequence-based methods applied to cyber network datasets and threat detection. Bartley holds a Ph.D. in computer science and engineering, working on loosely and unstructured logical query optimization, and a B.S. in computer engineering with a focus on software design and AI.

Technical Ask-the-Experts

On Demand

Summary

In this session, we'll answer any additional questions that attendees may have, beyond those discussed during the sessions.

Speakers

Ozzy Johnson

Director, Solutions Engineering
NVIDIA

Ozzy Johnson is the Director of Solutions Engineering for NVIDIA Developer Programs, where he oversees a team providing technical guidance to NVIDIA Inception startups. With more than two decades of experience in technology, Ozzy has held senior positions across the public and private sector and startups.

Adriana Flores, PhD

Senior Manager, NVIDIA AI Solution Architecture
NVIDIA

Dr. Adriana Flores leads NVIDIA's AI and GenAI Solution Architecture team. Leveraging her extensive knowledge of NVIDIA AI technologies, she empowers clients and partners to navigate the dynamic world of AI solutions. With a diverse background in AI and HPC spanning roles at NVIDIA and Hewlett Packard Labs, Adriana plays a pivotal role in making AI accessible. Beyond her corporate achievements, Adriana's academic contributions include notable research in wireless communication systems and HPC interconnect networks. Holding a Ph.D. and M.S. in Electrical Engineering from Rice University, as well as a B.S. from ITESM, Monterrey, Mexico, her academic journey complements her technical corporate expertise. Join Adriana in enabling AI in the Enterprise through practical insights and collaboration.