Advertise on podcast: AI Stories

Our guest today is Dawn Choo, founder of Interview Master and ex Data Scientist from Amazon and Meta.  In our conversation, we first dive into Dawn's past Data Science projects at Amazon and Instagram. She explains how a pet project skyrocketed her career at Amazon and also shares details on the most impactful project that she worked on at Instagram.  We then discuss Dawn's experience living in a van for a year before digging into Interview Master: a platform to help Data Scientists and Data Analysts land their dream job while leveraging AI agents to provide instant feedback!  If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. 👉 From beginner to advanced LLM developer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/beginner-to-advanced-llm-dev?ref=63e5e3 Link to Interview Master: https://www.interviewmaster.ai/ Follow Dawn on LinkedIn: https://www.linkedin.com/in/data-dawn/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) Intro (02:30) How Dawn Got Into Data and AI (04:25) Why Dawn Left Finance (06:56) Automating Work at Amazon (10:22) How a Pet Project Changed her Career (15:24) Joining Instagram (17:30) Instagram Shopping (20:52) Improving Performance and Revenue at Instagram (29:56) Living and Working from a Van (37:34) Launching Interview Master (45:53) Why Data Scientists Don’t Get Hired (53:27) Career Advice

Our guest today is Ritchie Vink, CEO & Founder of Polars: an open source data manipulation library known for being extremely fast. As of today, polars has over 32k stars on github.  In our conversation, Ritchie first explains how Polar which started as a side project evolved to what it is today. We then discuss the differences between Polars and Pandas, why Polars is fast and optimised and dig into Polars cloud: a platform which manages the compute infrastructure, allowing users to focus solely on writing queries.  If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. 👉 From beginner to advanced LLM developer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/beginner-to-advanced-llm-dev?ref=63e5e3 Link to Polars: https://pola.rs/ Follow Ritchie on LinkedIn: https://www.linkedin.com/in/ritchievink/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) Intro (02:23) How Ritchie got into Data & AI (08:00) How Polars started (12:02) Query Optimization (14:38) Polars vs. Pandas (22:16) Why Pandas is still popular (27:52) Polars Cloud (34:45) Polars’ Challenges & Future Roadmap (40:57) Career Advice

Our guest is Philippe Mizrahi, CEO of Linkup: a french startup building the world's best search agents.  In our conversation, Philippe first shares how he got into search by building an internal dataset search tool at Lyft. We then dive into Linkup where Phil explains how linkup started, how it evolved and how they managed to build the best search agents achieving state-of-the-art results on OpenAI SimpleQA dataset.  If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. 👉 From beginner to advanced LLM developer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/beginner-to-advanced-llm-dev?ref=63e5e3 Link to Linkup: https://www.linkup.so/ Follow Philippe on LinkedIn: https://www.linkedin.com/in/philippe-mizrahi/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) Intro (03:13) How Philippe Got into AI  (06:03) Building Lyft’s Internal Search Tool (11:40) How Linkup Started (16:10) How to use Linkup (21:55) Search Agents (31:58) Competing with OpenAI Operator (36:47) Use Cases of Linkup (42:28) Phil's Challenges as a CEO (51:06) Career Advice

Our guest is Samuel Colvin, Co-Founder and CEO of pydantic: a data validation library with millions of downloads per month.  In our conversation, we first discuss Pydantic and their observability platform: logfire. We then dive into agents where Samuel shares his vision on how to build production ready agents and what makes PydanticAI different than other frameworks.  If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. 👉 From beginner to advanced LLM developer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/beginner-to-advanced-llm-dev?ref=63e5e3 👉 8-hour GenAI Primer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/8-hour-genai-primer?ref=63e5e3 Follow Samuel on LinkedIn: https://www.linkedin.com/in/samuel-colvin/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) Intro (02:10) How Samuel Got into AI (04:06) What is Pydantic? (06:44) Observability with Logfire (13:28) PydanticAI (17:33) Agent Frameworks (24:40) PydanticAI vs Other Agent Frameworks (32:06) Strengths and Weaknesses of Agents (36:43) Future Challenges with AI Agents (46:45) Career Advice 

👉 From beginner to advanced LLM developer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/beginner-to-advanced-llm-dev?ref=63e5e3 👉 8-hour GenAI Primer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/8-hour-genai-primer?ref=63e5e3 Our guest today is Max Buckley, Senior Software Engineer at Google.  From business analyst intern to Senior LLM engineer at Google! Max has been at Google for 11+ years and what a great career he’s had! Max probably knows Google better than anyone else.  In our conversation, we go through Max's career with over 11 years of experience working at Google. We start with his first internship as a business analyst before he transitioned to software and then data engineering roles. In 2022, Max transitioned again and started building AI projects for Google including an Anti Money Laundering algorithm and internal RAG systems. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. Follow Max on LinkedIn: https://www.linkedin.com/in/maxbuckley/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) Intro (05:37) Internship to Full-Time Job at Google (07:20) Career Evolution Across 10+ Teams (10:30) Learning Through Side Projects (18:22) Joining Google Cloud AI (25:58) First AI Project (31:14) AML AI Project Breakdown (37:34) Shifting to LLMs (42:33) Retrieval & Contextual Chunking (47:28) Limitations of RAG (50:44) Google’s Evolution Over 10 Years (54:46) Career Advice 

👉 From beginner to advanced LLM developer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/beginner-to-advanced-llm-dev?ref=63e5e3 👉 8-hour GenAI Primer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/8-hour-genai-primer?ref=63e5e3 Our guest today is Wojtek Kuberski, Co-Founder and CTO at NannyML. In our conversation, we first discuss Wojtek's experience working as a freelancer. We then talk about NannyML: the platform for post deployment Data Science. We dive deep into model monitoring and discuss the key causes of model failure including covariate shift, concept drift and bad data quality. Wojtek also explains how NannyML's algorithms can estimate model performance without access to labels. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. Check out NannyML: https://www.nannyml.com/ Follow Wojtek on LinkedIn: https://www.linkedin.com/in/wojtek-kuberski/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) Intro (02:36) How Wojtek got into AI (04:48) Early Projects & Learnings in Freelance (13:40) Building NannyML (16:20) Model Monitoring (18:32) Covariate Shift vs Concept Drift (24:57) Technical Insights into Model Monitoring (27:56) NannyML’s Platform & Workflow  (35:50) Retraining Model & Model Failures (41:39) Future of NannyML  (47:09) Career Advice 

Our guest today is Thomas Scialom, Senior Staff Research Scientist at Meta. In our conversation, we first discuss Thomas' PhD where he explains how he managed to publish around 20 academic papers. We then dive into several LLMs that Thomas built at Meta including Galactica, Llama 2 and Llama 3. We finally dig into AI Agents, their limitations and how close we are to AGI and ASI. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. 👉 From beginner to advanced LLM developer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/beginner-to-advanced-llm-dev?ref=63e5e3 👉 8-hour GenAI Primer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/8-hour-genai-primer?ref=63e5e3 ToolFormer paper: https://arxiv.org/abs/2302.04761 To learn more about Llama 2: https://www.llama.com/llama2/ To learn more about Llama 3: https://www.llama.com/ Follow Thomas on LinkedIn: https://www.linkedin.com/in/tscialom/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) Intro   (02:28) How Thomas got into AI & ML (07:20) Publishing Academic Papers (14:48) Joining Meta (16:09) About Toolformer, ChatGPT & Galactica (19:20) Meta’s Response to ChatGPT (23:53) Scaling and Building LLMs (31:38) Why Open Source Matters (33:33) Thomas’ role in building Llama 3 (37:22) AI Agents  (42:13) AGI  (46:34) Current challenges faced with AI Agents (51:03) Career Advice

Our guest today is Başak Eskili, Machine Learning Engineer at Booking.com and C-Founder of Marvelous MLOps. In our conversation, we first dive into MLOps, its key components and how Başak got into the field. We then talk about Marvelous MLOps and her new course: "End to end MLOps with Databricks". Başak finally shares more about her current role at Booking with a focus on building feature stores. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. From beginner to advanced LLM developer course by Towards AI (use the code AISTORIES10 to get a 10% discount): https://academy.towardsai.net/courses/beginner-to-advanced-llm-dev?ref=63e5e3 To learn more about Marvelous MLOps: https://www.marvelousmlops.io/ End to End MLOps course with Databricks: https://maven.com/marvelousmlops/mlops-with-databricks Follow Başak on LinkedIn: https://www.linkedin.com/in/ba%C5%9Fak-tu%C4%9F%C3%A7e-eskili-61511b58/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) Intro   (02:18) How Başak Got into AI & MLOps   (06:55) Key Components of MLOps   (12:05) Deploying First ML Model   (15:58) Joining Booking.com   (18:11) Best Practices for Building Scalable and Reliable ML Systems   (23:01) Databricks  (27:50) Batch vs. Real-Time Predictions   (31:15) Marvelous MLOps   (33:52) Role at Booking.com   (35:45) Feature Stores  (45:45) Career Advice  

Our guest today is Max Mergenthaler, Co-Founder and CEO of Nixtla: one of the most popular libraries for time series forecasting. In this conversation, Max first explains how he got into AI and the lessons he learned from building a couple of tech startups. We then dive into Nixtla and forecasting. Max explains how he founded Nixtla and the different libraries available to build stats, ml and deep learning forecasting algorithms. We also tallk about TimeGPT, Nixtla's closed-source foundation model for time series. We finally discuss the future of the field along with mistakes and best practices when working on forecasting projects. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. To learn more about Nixtla: https://www.nixtla.io/ Open source librairies (StatsForecast, MLForecast, NeuralForecast): https://www.nixtla.io/open-source TimeGPT: https://github.com/Nixtla/nixtla Follow Max on LinkedIn: https://www.linkedin.com/in/mergenthaler/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) - Intro (02:00) - How Max got into Data & AI (03:44) - Combining Philosophy with Analytics (09:49) - Lessons from building Startups (14:00) - Founding Nixtla (16:23) - Time Series Forecasting (19:25) - StatsForecast, MLForecast, and NeuralForecast (26:16) - TimeGPT & LLMs for Forecasting (34:30) - Why people love Nixtla (42:34) - Future of Forecasting (45:51) - Mistakes & Best Practices in Forecasting (52:12) - Max’s role as CEO  (56:09) - Career Advice

Our guest today is Sebastian Raschka, Senior Staff Research Engineer at Lightning AI and bestselling book author. In our conversation, we first talk about Sebastian's role at Lightning AI and what the platform provides. We also dive into two great open source libraries that they've built to train, finetune, deploy and scale LLMs.: pytorch lightning and litgpt. In the second part of our conversation,  we dig into Sebastian's new book: "Build and LLM from Scratch". We discuss the key steps needed to train LLMs, the differences between GPT-2 and more recent models like Llama 3.1, multimodal LLMs and the future of the field. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. Build a Large Language Model From Scratch Book: https://www.amazon.com/Build-Large-Language-Model-Scratch/dp/1633437167 Blog post on Multimodal LLMs: https://magazine.sebastianraschka.com/p/understanding-multimodal-llms Lightning AI (with pytorch lightning and litgpt repos): https://github.com/Lightning-AI Follow Sebastian on LinkedIn: https://www.linkedin.com/in/sebastianraschka/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) - Intro (02:27) - How Sebastian got into Data & AI (06:44) - Regressions and loss functions (13:32) - Academia to joining LightningAI (21:14) - Lightning AI VS other cloud providers (26:14) - Building PyTorch Lightning & LitGPT (30:48) - Sebastian’s role as Staff Research Engineer (34:35) - Build an LLM From Scratch (45:00) - From GPT2 to Llama 3.1 (48:34) - Long Context VS RAG (56:15) - Multimodal LLMs (01:03:27) - Career Advice

Our guest today is Loubna Ben Allal, Machine Learning Engineer at Hugging Face 🤗 . In our conversation, Loubna first explains how she built two impressive code generation models: StarCoder and StarCoder2. We dig into the importance of data when training large models and what can be done on the data side to improve LLMs performance. We then dive into synthetic data generation and discuss the pros and cons. Loubna explains how she built Cosmopedia, a dataset fully synthetic generated using Mixtral 8x7B. Loubna also shares career mistakes, advice and her take on the future of developers and code generation.  If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. Cosmopedia Dataset: https://huggingface.co/blog/cosmopedia StarCoder blog post: https://huggingface.co/blog/starcoder Follow Loubna on LinkedIn: https://www.linkedin.com/in/loubna-ben-allal-238690152/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) - Intro (02:00) - How Loubna Got Into Data & AI (03:57) - Internship at Hugging Face (06:21) - Building A Code Generation Model: StarCoder (12:14) - Data Filtering Techniques for LLMs (18:44) - Training StarCoder (21:35) - Will GenAI Replace Developers?  (25:44) - Synthetic Data Generation & Building Cosmopedia (35:44) - Evaluating a 1B Params Model Trained on Synthetic Data (43:43) - Challenges faced & Career Advice

Our guest today is Petar Veličković, Staff Research Scientist at Google DeepMind and Affiliated Lecturer at University of Cambridge. In our conversation, we first dive into how Petar got into Graph ML and discuss his most cited paper: Graph Attention Networks. We then dig into DeepMind where Petar shares tips and advice on how to get into this competitive company and explains the difference between research scientists and research engineering roles. We finally talk about applied work that Petar worked on including building Google Maps' ETA algorithm and an AI coach football coach assistant to help Liverpool FC improve corner kicks. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. Graph Attention Networks Paper: https://arxiv.org/abs/1710.10903 ETA Prediction with Graph Neural Networks in Google Maps: https://arxiv.org/abs/2108.11482 TacticAI: an AI assistant for football tactics (with Liverpool FC): https://arxiv.org/abs/2402.01306 Follow Petar on LinkedIn: https://www.linkedin.com/in/petarvelickovic/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) - Intro (02:44) - How Petar got into AI (06:14) - GraphML and Geometric Deep Learning (10:10) - Graph Attention Networks (17:00) - Joining DeepMind (20:24) - What Makes DeepMind People Special? (22:28) - Getting into DeepMind (24:36) - Research Scientists Vs Research Engineer (30:40) - Petar's Career Evolution at DeepMind (35:20) - Importance of Side Projects (38:30) - Building Google Maps ETA Algorithm (47:30) - Tactic AI: Collaborating with Liverpool FC (01:03:00) - Career advice 

Our guest today is Lewis Tunstall, LLM Engineer and researcher at Hugging Face and book author of "Natural Language Processing with Transformers". In our conversation, we dive into topological machine learning and talk about giotto-tda, a high performance topological ml Python library that Lewis worked on. We then dive into LLMs and Transformers. We discuss the pros and cons of open source vs closed source LLMs and explain the differences between encoder and decoder transformer architectures. Lewis finally explains his day-to-day at Hugging Face and his current work on fine-tuning LLMs. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. Link to Train in Data courses (use the code AISTORIES to get a 10% discount): https://www.trainindata.com/courses?affcode=1218302_5n7kraba Natural Language Processing with Transformers book: https://www.oreilly.com/library/view/natural-language-processing/9781098136789/ Giotto-tda library: https://github.com/giotto-ai/giotto-tda KTO alignment paper: https://arxiv.org/abs/2402.01306 Follow Lewis on LinkedIn: https://www.linkedin.com/in/lewis-tunstall/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) - Intro (03:00) - How Lewis Got into AI (05:33) - From Kaggle Competitions to Data Science Job (11:09) - Get an actual Data Science Job! (15:18) - Deep Learning or Excel? (19:14) - Topological Machine Learning (28:44) - Open Source VS Closed Source LLMs (41:44) - Writing a Book on Transformers (52:33) - Comparing BERT, Early Transformers, and GPT-4 (54:48) - Encoder and Decoder Architectures (59:48) - Day-To-Day Work at Hugging Face (01:09:06) - DPO and KTO (01:12:58) - Stories and Career Advice

Our guest today is Maria Vecthomova, ML Engineering Manager at Ahold Delhaize and Co-Founder of Marvelous MLOps. In our conversation, we first talk about code best practices for Data Scientists. We then dive into MLOps, discuss the main components required to deploy a model in production and get an overview of one of Maria's project where she built and deployed a fraud detection algorithm. We finally talk about content creation, career advice and the differences between an ML and an MLOps engineer. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. Link to Train in Data courses (use the code AISTORIES to get a 10% discount): https://www.trainindata.com/courses?affcode=1218302_5n7kraba Check out Marvelous MLOps: https://marvelousmlops.substack.com/ Follow Maria on LinkedIn: https://www.linkedin.com/in/maria-vechtomova/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) - Intro (02:59) - Maria’s Journey to MLOps (08:50) - Code Best Practices (18:39) - MLOps Infrastructure (29:10) - ML Engineering for Fraud Detection (40:42) - Content Creation & Marvelous MLOps (49:01) - ML Engineer vs MLOps Engineer (56:00) - Stories & Career Advice

Our guest today is Reah Miyara. Reah is currently working on LLMs evaluation at OpenAI and previously worked at Google and IBM. In our conversation, Reah shares his experience working as a product lead for Google's graph-based machine learning portfolio. He then explains how he joined OpenAI and his role there. We finally talk about LLMs evaluation, AGI, LLMs safety and the future of the field. If you enjoyed the episode, please leave a 5 star review and subscribe to the AI Stories Youtube channel. Link to Train in Data courses (use the code AISTORIES to get a 10% discount): https://www.trainindata.com/courses?affcode=1218302_5n7kraba Follow Reah on LinkedIn: https://www.linkedin.com/in/reah/ Follow Neil on LinkedIn: https://www.linkedin.com/in/leiserneil/   --- (00:00) - Intro (03:09) - Getting into AI and Machine Learning (08:33) - Why Stay in AI? (11:39) - From Software Engineer to Product Manager (18:27) - Experience at Google (25:28) - Applications of Graph ML  (31:10) - Joining OpenAI (35:15) - LLM Evaluation (44:30) - The Future of GenAI and LLMs  (55:48) - Safety Metrics for LLMs (1:00:30) - Career Advice