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=63e5e3Link 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=63e5e3Link 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=63e5e3Link 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=63e5e3Follow 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 

Max Buckley, a Senior Software Engineer at Google with over 11 years of experience, shares insights from his remarkable journey from intern to LLM engineer. He discusses the evolution of his roles, the importance of continuous learning through side projects, and his groundbreaking work on AI for anti-money laundering. Max highlights the exciting advancements in large language models and Retrieval-Augmented Generation, as well as changes in Google's corporate culture. His story emphasizes proactive career management and the significance of mentorship in tech.

Wojtek Kuberski, Co-Founder and CTO at NannyML, shares his expertise in AI and data science. He discusses the challenges of model monitoring post-deployment, including covariate shift and concept drift. Wojtek explains how NannyML's algorithms assess model performance without needing labels. He emphasizes the critical role of continuous monitoring to prevent silent failures that could impact businesses. The conversation also touches on his transition from freelancing to building a product-focused company in the ever-evolving data science landscape.

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=63e5e3ToolFormer paper: https://arxiv.org/abs/2302.04761To 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

In this discussion, Başak Eskili, a Machine Learning Engineer at Booking.com and co-founder of Marvelous MLOps, shares her inspiring journey into the world of MLOps. She highlights key components like version control and CI/CD pipelines that are essential for effective machine learning operations. The conversation dives into the significance of feature stores in real-time applications and the best practices for building scalable ML systems. Başak also offers valuable career advice for aspiring ML professionals, emphasizing the importance of soft skills in tech.

Max Mergenthaler, Co-founder and CEO of Nixtla, shares his journey from philosophy to building innovative forecasting libraries. He discusses founding Nixtla and its popular tools like StatsForecast, MLForecast, and NeuralForecast. The conversation highlights TimeGPT, an advanced model for time series analysis, emphasizing its potential over traditional methods. Max also touches on best practices and common pitfalls in forecasting, along with the evolving role of data scientists in this rapidly changing field.

Sebastian Raschka, a Senior Staff Research Engineer at Lightning AI and bestselling author, dives into the art of building large language models. He shares insights on two significant open-source libraries, PyTorch Lightning and LitGPT, that enhance LLM training and deployment. The discussion shifts to his new book, where he outlines essential steps in LLM training and contrasts models like GPT-2 with the latest Llama 3. Sebastian also explores the universe of multimodal LLMs and their potential, highlighting exciting developments on the horizon.