Primer.AI x DataScience SG
Details
For March, we are partnering with Primer.AI again! They will be sharing the deployment of LLMs products together with more insights on the development of RAGs.
Agenda
6.30pm - 7.00pm: Registration
7.00pm - 7.45pm: Deploying NLP and LLM Products for Real-Time Insights
7.45pm - 8.30pm: The Evolution and Future of Retrieval-Augmented Generation (RAG) Frameworks
8.30pm - 9.00pm: Q&A
Part I: Deploying NLP and LLM Products for Real-Time Insights
Speaker: Thomas See, Senior Solutions Engineer, Primer AI
The first segment of our sharing will explore how Primer harnesses the power of both "traditional" NLP methodologies and the latest advancements in LLMs. Thomas will provide a comprehensive demo illustrating how these technologies are deployed within live SaaS applications, specifically focusing on handling large, streaming datasets like news and social media feeds and the trade-offs between utilizing NLP and LLMs. He will share insights into the practical challenges and solutions involved in real-world AI product deployment.
Part 2: The Evolution and Future of Retrieval-Augmented Generation (RAG) Frameworks
Speaker: Zhuang Qiang (ZQ), Staff Data Scientist, Primer AI.
It has been more than a year since ChatGPT took the world by storm, spurring a widespread and explosive interest in large language models (LLMs) we are experiencing today. Retrieval augmented generation (RAG) is a method/framework for overcoming the limitations of LLMs that quickly followed. RAG has today become ubiquitous for the application of LLMs, with a rich ecosystem of tools and other innovations developed over the last year.
In this session, ZQ will do a review of some of these new tools and innovations, factoring in Primer’s insights from building a best-in-class LLM powered application for a highly discerning and sophisticated client base in defense and national security. We will also discuss some of the current challenges and emerging ideas for building with LLMs.
Speaker Bio
Thomas is a Senior Solutions Engineer at Primer.ai, with a background in product management. Before joining Primer, he served as Senior Product Manager at GIC Labs where he spearheaded the validation and implementation of emerging technologies for a broad range of investment use cases. He has successfully led projects in advanced portfolio analytics, digital document processing, and leveraging alternative data for private equity due diligence. He holds dual Degrees in Finance and Accountancy from Nanyang Technological University.
Zhuang Qiang (ZQ) is a Staff Data Scientist in Primer.ai, and a data scientist and machine learning engineer with over a decade of experience in machine learning and natural language processing. He has served in various roles and levels across a range of industries and companies, pioneering the use of these technologies for some of the most challenging business problems across defense, finance and social media. He holds dual Masters Degrees in Electrical Engineering (Pattern Recognition), and Computer Science (Machine Learning) from the National University of Singapore and Georgia Institute of Technology respectively, and achieved the rank of Kaggle Competition Expert when he was active some years ago.
About Primer AI
Primer is a leading Natural Language Processing (NLP) company headquartered in San Francisco. Primer's awards include CB Insights Top 100 AI company 2018 & 2020, Intelligent Applications Top 40 (2021), Data50 Global #3 rank in the AI/ML segment and has been recentlynamed 2024 Top 50 AI company championing American Dynamism by A16z.
Primer’s NLP and LLM technology is deployed by the U.S. Government and Fortune 100 companies to help analysts and operators extract timely insight and decision advantage from massive datasets. Primer’s offices are in San Francisco, Washington DC and Singapore.
