<![CDATA[Chengyin Eng: Speaking]]>https://www.chengyineng.com/s/speakinghttps://substackcdn.com/image/fetch/$s_!mBDd!,w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F06a6af98-6e11-4a35-ac44-46a57b8cdad6_1280x1280.pngChengyin Eng: Speakinghttps://www.chengyineng.com/s/speakingSubstackSun, 05 Apr 2026 13:45:30 GMT<![CDATA[Scaling Data Workloads]]>https://www.chengyineng.com/p/scaling-data-workloadshttps://www.chengyineng.com/p/scaling-data-workloadsWed, 25 Sep 2024 23:28:01 GMTWatch on YouTube

]]><![CDATA[Designing Better MLOps Systems]]>https://www.chengyineng.com/p/designing-better-mlops-systemshttps://www.chengyineng.com/p/designing-better-mlops-systemsWed, 25 Sep 2024 23:26:37 GMTWatch on YouTube

]]><![CDATA[Ask Me Anything: MLflow, MLOps, MLflow Pipelines]]>https://www.chengyineng.com/p/ask-me-anything-mlflow-mlops-mlflowhttps://www.chengyineng.com/p/ask-me-anything-mlflow-mlops-mlflowWed, 25 Sep 2024 23:25:28 GMT

]]><![CDATA[The Future of MLOps and NLP]]>https://www.chengyineng.com/p/the-future-of-mlops-and-nlphttps://www.chengyineng.com/p/the-future-of-mlops-and-nlpWed, 25 Sep 2024 23:23:53 GMTListen Here

]]><![CDATA[Charting Your Career Growth]]>https://www.chengyineng.com/p/charting-your-career-growthhttps://www.chengyineng.com/p/charting-your-career-growthWed, 25 Sep 2024 23:22:08 GMTDownload Slides

]]><![CDATA[How Not to Let Your Model and Data Drift Away Silently]]>https://www.chengyineng.com/p/how-not-to-let-your-model-and-datahttps://www.chengyineng.com/p/how-not-to-let-your-model-and-dataWed, 25 Sep 2024 23:21:16 GMTDownload Slides and Code

]]><![CDATA[A Foray into Nested Data using Spark SQL]]>https://www.chengyineng.com/p/a-foray-into-nested-data-using-sparkhttps://www.chengyineng.com/p/a-foray-into-nested-data-using-sparkWed, 25 Sep 2024 23:19:37 GMTWatch on YouTube

Nested data is often our least favorite type of data since it can be challenging and time-consuming to wrangle. In this workshop, we distill foundational concepts about two common types of nested columns: arrays and structs. Using SQL Analytics, we will be exploring a dataset curated by the Manhattan Chocolate Society on dark chocolate with varying flavors, ratings, and places of origin. You will learn how to create nested data from flat data, manipulate and conduct aggregate calculations on nested columns; and also perhaps more importantly, about chocolate!

Collaboration with Fred Abood.

]]><![CDATA[Exploring Police Fatal Force with Databricks SQL]]>https://www.chengyineng.com/p/exploring-police-fatal-force-withhttps://www.chengyineng.com/p/exploring-police-fatal-force-withWed, 25 Sep 2024 23:18:28 GMTWatch on YouTube

]]><![CDATA[Ensuring Machine Learning Reproducibility with Delta and MLflow]]>https://www.chengyineng.com/p/ensuring-machine-learning-reproducibilityhttps://www.chengyineng.com/p/ensuring-machine-learning-reproducibilityWed, 25 Sep 2024 23:17:41 GMTDownload Slides

]]><![CDATA[Intro to Python on Databricks Workshop]]>https://www.chengyineng.com/p/intro-to-python-on-databricks-workshophttps://www.chengyineng.com/p/intro-to-python-on-databricks-workshopWed, 25 Sep 2024 23:16:15 GMTWatch on YouTube

During this stay-at-home season, we want to help you learn a new skill! Whether you are middle-schoolers, college students, working professionals, etc., if you are interested in learning Python, come join the completely free, live workshop!

]]><![CDATA[Analyzing COVID-19: Can the Data Community Help?]]>https://www.chengyineng.com/p/analyzing-covid-19-can-the-data-communityhttps://www.chengyineng.com/p/analyzing-covid-19-can-the-data-communityWed, 25 Sep 2024 23:14:46 GMTWatch on YouTube

]]><![CDATA[LLMs: Foundation Models from the Ground Up]]>https://www.chengyineng.com/p/llms-foundation-models-from-the-groundhttps://www.chengyineng.com/p/llms-foundation-models-from-the-groundWed, 25 Sep 2024 23:13:04 GMTWatch on YouTube

Refer to Part 1 here.

]]><![CDATA[LLMs: Application through Production]]>https://www.chengyineng.com/p/llms-application-through-productionhttps://www.chengyineng.com/p/llms-application-through-productionWed, 25 Sep 2024 23:11:52 GMTWatch on YouTube

I co-teach this course with Matei Zaharia, Sam Raymond, and Joseph Bradley.

This course is aimed at developers, data scientists, and engineers looking to build LLM-centric applications with the latest and most popular frameworks. You will use Hugging Face to solve natural language processing (NLP) problems, leverage LangChain to perform complex, multi-stage tasks, and deep-dive into prompt engineering. You will use data embeddings and vector databases to augment LLM pipelines. Additionally, you will fine-tune LLMs with domain-specific data to improve performance and cost, as well as identify the benefits and drawbacks of proprietary models. You will assess societal, safety, and ethical considerations of using LLMs. Finally, you will learn how to deploy your models at scale, leveraging LLMOps best practices.

By the end of this course, you will have built an end-to-end LLM workflow that is ready for production!

Refer to Part 2 here:

]]><![CDATA[Unveiling LLM Challenges and Their Emerging Solutions]]>https://www.chengyineng.com/p/unveiling-llm-challenges-and-theirhttps://www.chengyineng.com/p/unveiling-llm-challenges-and-theirWed, 25 Sep 2024 23:09:32 GMT

Download slides

]]>