Munich MLOps Community Meetup #9
Hello, fellow MLOps Engineers and ML Enthusiasts, ready for a new neetup?
We're announcing our next meetup event - on Wednesday, September 18th at 18:30, at Wayra Deutschland (near Marienplatz station).
Full agenda announced:
18:30 - 18:50 - Drinks & Networking
18:50 - 19:00 - Welcome
19:00 - 19:40 - Talk #1: Observability and Evaluation of Large Language Model Applications - Petr Polezhaev, Senior Data Scientist at SIXT
19:40 - 20:20 - Talk #2: Deploying MLOps Tooling Across Multiple Stacks and Cloud Providers - Ali Abbas Jaffri, ML Platform Engineer at Synthesia
20:20 - Onwards - Drinks, food & networking
More about the Talks:
Talk #1: Observability and Evaluation of Large Language Model Applications:
The topic of generative AI has recently gained significant popularity. With the help of proprietary and open source large language models (LLMs), many companies, start-ups, and researchers are exploring the potential of these models to develop new products or improve existing ones. LLMs are widely used for various tasks such as text summarisation, translation, stylisation, information extraction, question answering, and content generation. However, the evaluation of these models is often limited to human-based assessments, which is not scalable and limits the ability to conduct experiments.
In this talk, we will explore the approaches to perform evaluation at both the end-to-end and task levels using classical machine learning and business metrics. We will compare different approaches to perform evaluation, such as LLM as a Judge, G-Eval, RAGAS and ARES.Talk #2: Deploying MLOps Tooling Across Multiple Stacks and Cloud Providers:
Deploying MLOps tooling across various cloud providers and stacks can be a complex and daunting task. In this talk, we will cover how to effectively implement the right MLOps tools, starting from a local development environment to deployment across multiple cloud platforms. Additionally, we will explore strategies for deploying these tools and provide insights on planning for scalability.
More about the Speakers:
Speaker #1: Petr (LinkedIn) is a Senior Data Scientist at SIXT, focusing on NLP and Generative AI. Previously, he worked as a data scientist in technology companies, creating data products for industry and academia, including recommender systems for mobile applications and AI components for educational platforms.
Speaker #2: Ali (Linkedin) is an ML Platform Engineer at Synthesia, with a passion for building scalable and efficient systems. Over the past year, he has been focused on developing mlinfra, a tool that simplifies the deployment of MLOps tooling across different cloud providers and environments. This allows MLOps engineers to concentrate on selecting the right tools for their needs, without the burden of managing underlying infrastructure.
Looking forward to your RSVPs and to meeting you there!
Keep on hacking!🤩🤩🤩