Pipeline Conversations
Episode Archive
Episode Archive
32 episodes of Pipeline Conversations since the first episode, which aired on November 19th, 2021.
-
The Evaluation Playbook: Making LLMs Production-Ready 🧪📈
December 15th, 2024 | Season 3 | 32 mins 43 secs
ai, evaluation, genai, llmops, llms, mlops
A comprehensive exploration of real-world lessons in LLM evaluation and quality assurance, examining how industry leaders tackle the challenges of assessing language models in production.
-
Prompt Engineering & Management in Production: Practical Lessons from the LLMOps Database
December 11th, 2024 | Season 3 | 29 mins 34 secs
ai, genai, llmops, llms, mlops, prompt-engineering, prompts
Prompt engineering is the art and science of crafting instructions that unlock the potential of large language models (LLMs). It's a critical skill for anyone working with LLMs, whether you're building cutting-edge applications or conducting fundamental research. But what does effective prompt engineering look like in practice, and how can we systematically improve our prompts over time?
-
LLM Agents in Production: Architectures, Challenges, and Best Practices
December 9th, 2024 | Season 3 | 32 mins 37 secs
agents, ai, genai, llmops, llms, mlops
An in-depth exploration of LLM agents in production environments, covering key architectures, practical challenges, and best practices.
-
Building Advanced Search, Retrieval, and Recommendation Systems with LLMs
December 6th, 2024 | Season 3 | 13 mins 8 secs
ai, embeddings, genai, llmops, llms, mlops, rag, recommendation, search
Discover how embeddings power modern search and recommendation systems with LLMs.
-
Building LLM Applications that Know What They're Talking About 🔓🧠
December 3rd, 2024 | Season 3 | 21 mins 23 secs
ai, genai, llmops, llms, mlops, rag
A conversation about the RAG entries in the ZenML LLMOps database
-
Demystifying LLMOps: A Practical Database of Real-World Generative AI Implementations
December 2nd, 2024 | Season 3 | 15 mins 2 secs
genai, llmops
NotebookLM summary podcast episode of a ZenML blog around the LLMOps Database.
-
ML at the British Library with Daniel van Strien
November 10th, 2022 | Season 2 | 57 mins 28 secs
ai, archives, computer-vision, data-science, libraries, machine-learning
This week I spoke with Daniel van Strien, a digital curator working at the British Library. Daniel has worked on a number of projects at the intersection of archives, libraries and machine learning and I was really happy to have the chance to get to unpack some of the ways he's finding to apply these techniques and tools.
-
Questioning MLOps with Lak Lakshmanan
October 27th, 2022 | Season 2 | 53 mins 2 secs
ai, artificial-intelligence, data-science, infrastructure, machine-learning, mlops, scale
This week I spoke with Lak Lakhshmanan, who worked for years at Google on ML and AI projects and products at a senior level and he also brings years of experience working on meteorology and other scientific projects previously.
-
The Full Stack with Charles Frye
October 12th, 2022 | Season 2 | 57 mins 5 secs
ai, artificial-intelligence, data-science, deep-learning, education, machine-learning, mlops
This week I spoke with Charles Frye. Not only has Charles volunteered to be a judge on our Month of MLOps competition happening right now, he's part of the core team working on the Full Stack Deep Learning course.
-
Educating the next generation with Goku Mohandas
September 29th, 2022 | Season 2 | 1 hr 8 mins
ai, artificial-intelligence, data-science, education, infrastructure, machine-learning, medicine, mlops
In today's conversation, I'm speaking with Goku Mohandas, founder and creator of the amazing online resource MadeWithML. Goku has a bunch of practical experience, from working with Apple to a startup in the oncology space and much more.
-
ZenML MLOps Competition
September 26th, 2022 | Season 2 | 8 mins 13 secs
competition, mlops, open-source, zenml
So excited to be able to announce our :fire: AMAZING :fire: external judges for the ZenML Month of MLOps competition! We have a stellar panel of :sparkles: ML and MLOps heroes :sparkles: to help select the best pipelines from all of your submissions!
-
Data-centric Computer Vision with Eric Landau
September 15th, 2022 | Season 2 | 51 mins 51 secs
annotation, computer-vision, data-centric-ai, engineering, machine-learning
This week I spoke with Eric Landau, co-founder of Encord, a platform for data-centric computer vision. This podcast contains a lot of geekery about annotation, and even though Encord aren't an annotation tool per se, Eric and his team have tackled a bunch of quite complicated problems relating to that domain.
-
ML Abstractions with Phil Howes
September 5th, 2022 | Season 2 | 54 mins 13 secs
ai, data-science, infrastructure, machine-learning, mlops, pipelines, platforms, tools
This week we dive into the abstractions that we're all trying to layer on top of the core ML processes and workflows. I spoke with Phil Howes, co-founder and chief scientist at BaseTen. BaseTen is a platform that allows data scientists to go from an initial model to an MVP web app quickly.
-
Building MLOps Tools with Outerbounds
August 22nd, 2022 | Season 2 | 59 mins 43 secs
ai, data-science, infrastructure, machine-learning, mlops, pipelines, tools
This week I spoke with Savin Goyal and Hugo Bowne-Anderson from Outerbounds. They both work on leading, building and helping people put models into production through Metaflow, and I'm sure current users of ZenML will find this conversation interesting to hear how they think through the broader questions and engineering problems involved with MLOps.
-
Safe and Testable Computer Vision with Lakera
August 4th, 2022 | Season 2 | 57 mins 32 secs
computer-vision, data, machine-learning, mlops, monitoring, safety, testing
This week I spoke with Mateo Rojas-Carulla, the CTO and a co-founder of Lakera and Matthias Kraft, also a co-founder and the CPO there. Lakera is an AI safety company that does a lot of work in the computer vision domain, building a platform and tools for users to gain more confidence in the output and functionality of their models.
-
Satellite Vision with Robin Cole
July 28th, 2022 | Season 2 | 47 mins 56 secs
computer-vision, data-science, deep-learning, mlops, satellite, serverless
This week I spoke with Robin Cole, a senior data scientist at Satellite Vu, a company that's about to launch a thermal imaging satellite into space in order to provide new ways of seeing the earth from above.