You are viewing content from a past/completed conference.
GenAI for Productivity
At Wealthsimple, we leverage Generative AI internally to improve operational efficiency and streamline monotonous tasks. Our GenAI stack is a blend of tools we developed in house and third party solutions.
Roughly half of the company utilizes these tools in their day to day work. This talk will cover the tools we use, the lessons we learned and how user behavior drives the intersection behind LLMs for productivity.
Interview:
What is the focus of your work?
These days, most of my time goes into driving strategy for our ML Engineering and Data Engineering teams: how do we evolve these platforms to further democratize access to data and abstract the engineering complexities behind productionizing new AI/ML products?
What’s the motivation for your talk?
User behavior is an important aspect that is often overlooked when examining the intersection between GenAI and productivity. Over the past year, we have launched several new tools and learned many important lessons along the way. I would love to share these insights more broadly.
Who is your talk for?
Anyone who supports the rollout / strategy of Gen AI tools (engineering leaders, project managers, etc)
Is there anything specific that you'd like people to walk away with after attending your session?
The main takeaways I want them to walk away from are:
- The role user behavior plays in the change management process (for GenAI specifically)
- Some of the ways we have been effectively leveraging LLMs and multi stage retrieval systems to drive productivity internally
What do you think is the next big disruption in software?
Edge computing will be the key to commodizing Generative AI by unlocking smaller models available on our mobile devices.
Speaker
Mandy Gu
Senior Software Development Manager @Wealthsimple
Mandy is a Senior Software Development Manager at Wealthsimple, where she leads Machine Learning & Data Engineering. These teams provide a simple and reliable platform to empower the rest of the company to iterate quickly on machine learning applications, GenAI tools and leverage data assets to make better decisions. Previously, Mandy worked in the NLP space and as a data scientist..
Read more
From the same track
Session
AI/ML
Search: from Linear to Multiverse
Tuesday Nov 19 / 02:45PM PST
The future of search is undergoing a revolutionary transformation, shifting from traditional linear queries to a rich multiverse of possibilities powered by AI.
Faye Zhang
Staff Software Engineer @Pinterest, Tech Lead on GenAI Search Traffic Projects, Speaker, Expert in AI/ML with a Strong Background in Large Distributed System
Search: from Linear to Multiverse
Session
LLMOps
Navigating LLM Deployment: Tips, Tricks, and Techniques
Tuesday Nov 19 / 01:35PM PST
Self-hosted Language Models are going to power the next generation of applications in critical industries like financial services, healthcare, and defense.
Meryem Arik
Co-Founder @TitanML, Recognized as a Technology Leader in Forbes 30 Under 30, Recovering Physicist
Navigating LLM Deployment: Tips, Tricks, and Techniques
Session
AI/ML
10 Reasons Your Multi-Agent Workflows Fail and What You Can Do About It
Tuesday Nov 19 / 03:55PM PST
Multi-agent systems – a setup where multiple agents (generative AI models with access to tools) collaborate to solve complex tasks – are an emerging paradigm for building applications.
Victor Dibia
Principal Research Software Engineer @Microsoft Research, Core Contributor to AutoGen, Author of "Multi-Agent Systems with AutoGen" book. Previously @Cloudera, @IBMResearch
10 Reasons Your Multi-Agent Workflows Fail and What You Can Do About It
Session
Machine Learning
A Framework for Building Micro Metrics for LLM System Evaluation
Tuesday Nov 19 / 05:05PM PST
LLM accuracy is a challenging topic to address and is much more multi dimensional than a simple accuracy score. In this talk we’ll dive deeper into how to measure LLM related metrics, going through examples, case studies and techniques beyond just a single accuracy and score.
Denys Linkov
Head of ML @Voiceflow, LinkedIn Learning Instructor, ML Advisor and Instructor, Previously @LinkedIn
A Framework for Building Micro Metrics for LLM System Evaluation
Session
Scaling Large Language Model Serving Infrastructure at Meta
Tuesday Nov 19 / 10:35AM PST
Running LLMs requires significant computational power, which scales with model size and context length. We will discuss strategies for fitting models to various hardware configurations and share techniques for optimizing inference latency and throughput at Meta.
Ye (Charlotte) Qi
Senior Staff Engineer @Meta
Scaling Large Language Model Serving Infrastructure at Meta