Secret to Production AI: Tools & Infrastructure | Data Brew | Episode 37

Data Brew by Databricks

#Databricks #Data Analytics #Apache Spark #Delta Lake #Machine Learning #Data Engineering #Artificial Intelligence #Tech #Data Science #Science #Lifestyle #Podcasting Education

21:04

Step into the mysterious and visually stunning world of The Electric State as host Francesca Amiker takes you behind the scenes with the creative masterminds who brought Simon Stålenhag’s dystopian vision to life. In this premiere episode, directors Joe and Anthony Russo, stars Millie Bobby Brown and Chris Pratt, writers Christopher Markus and Stephen McFeely, and producers Angela Russo-Otstot and Chris Castaldi reveal how they transformed a haunting graphic novel into an epic cinematic experience. Watch The Electric State coming to Netflix on March 14th. Check out more from Netflix Podcasts . State Secrets: Inside the Making of The Electric State is produced by Netflix and Treefort Media.…

for ca. et år siden 37:14

MP3•Episode hjem

In this episode, Julia Neagu, CEO & co-founder of Quotient AI, explores the challenges of deploying Generative AI and LLMs, focusing on model evaluation, human-in-the-loop systems, and iterative development.
Highlights include:
- Merging reinforcement learning and unsupervised learning for real-time AI optimization.
- Reducing bias in machine learning with fairness and ethical considerations.
- Lessons from large-scale AI deployments on scalability and feedback loops.
- Automating workflows with AI through successful business examples.
- Best practices for managing AI pipelines, from data collection to validation.

42 episoder

Secret to Production AI: Tools & Infrastructure | Data Brew | Episode 37

Data Brew by Databricks

71 subscribers

published for ca. et år siden

Del

MP3•Episode hjem

42 episoder

#Databricks #Data Analytics #Apache Spark #Delta Lake #Machine Learning #Data Engineering #Artificial Intelligence #Tech #Data Science #Science #Lifestyle #Podcasting Education

Alle episoder

1
SWE-bench & SWE-agent | Data Brew | Episode 44 36:22

for 6 dage siden36:22

36:22

In this episode, Kilian Lieret, Research Software Engineer, and Carlos Jimenez, Computer Science PhD Candidate at Princeton University, discuss SWE-bench and SWE-agent, two groundbreaking tools for evaluating and enhancing AI in software engineering. Highlights include: - SWE-bench: A benchmark for assessing AI models on real-world coding tasks. - Addressing data leakage concerns in GitHub-sourced benchmarks. - SWE-agent: An AI-driven system for navigating and solving coding challenges. - Overcoming agent limitations, such as getting stuck in loops. - The future of AI-powered code reviews and automation in software engineering.…

1
Enterprise AI: Research to Product | Data Brew | Episode 43 38:03

for 13 dage siden38:03

38:03

In this episode, Dipendra Kumar, Staff Research Scientist, and Alnur Ali, Staff Software Engineer at Databricks, discuss the challenges of applying AI in enterprise environments and the tools being developed to bridge the gap between research and real-world deployment. Highlights include: - The challenges of real-world AI—messy data, security, and scalability. - Why enterprises need high-accuracy, fine-tuned models over generic AI APIs. - How QuickFix learns from user edits to improve AI-driven coding assistance. - The collaboration between research & engineering in building AI-powered tools. - The evolving role of developers in the age of generative AI.…

1
Multimodal AI | Data Brew | Episode 42 42:14

for 16 dage siden42:14

42:14

In this episode, Chang She, CEO and Co-founder of LanceDB, discusses the challenges of handling multimodal data and how LanceDB provides a cutting-edge solution. He shares his journey from contributing to Pandas to building a database optimized for images, video, vectors, and subtitles. Highlights include: - The limitations of traditional storage systems like Parquet for multimodal AI. - How LanceDB enables efficient querying and processing of diverse data types. - The growing importance of multimodal AI in enterprise applications. - Future trends in AI, including a shift from single models to holistic AI systems. - Predictions and "spicy takes" on AI advancements in 2025.…

1
Age of Agents | Data Brew | Episode 41 40:47

for 27 dage siden40:47

40:47

In this episode, Michele Catasta, President of Replit, explores how AI-driven agents are transforming software development by making coding more accessible and automating application creation. Highlights include: - The difference between AI agents and copilots in software development. - How AI is democratizing coding, enabling non-programmers to build applications. - Challenges in AI agent development, including error handling and software quality. - The growing role of AI in entrepreneurship and business automation. - Why 2025 could be the year of AI agents and what’s next for the industry.…

1
Reward Models | Data Brew | Episode 40 39:58

for 5 weeks siden39:58

39:58

In this episode, Brandon Cui, Research Scientist at MosaicML and Databricks, dives into cutting-edge advancements in AI model optimization, focusing on Reward Models and Reinforcement Learning from Human Feedback (RLHF). Highlights include: - How synthetic data and RLHF enable fine-tuning models to generate preferred outcomes. - Techniques like Policy Proximal Optimization (PPO) and Direct Preference Optimization (DPO) for enhancing response quality. - The role of reward models in improving coding, math, reasoning, and other NLP tasks. Connect with Brandon Cui: https://www.linkedin.com/in/bcui19/…

1
Retrieval, rerankers, and RAG tips and tricks | Data Brew | Episode 39 45:22

for 9 weeks siden45:22

45:22

In this episode, Andrew Drozdov, Research Scientist at Databricks, explores how Retrieval Augmented Generation (RAG) enhances AI models by integrating retrieval capabilities for improved response accuracy and relevance. Highlights include: - Addressing LLM limitations by injecting relevant external information. - Optimizing document chunking, embedding, and query generation for RAG. - Improving retrieval systems with embeddings and fine-tuning techniques. - Enhancing search results using re-rankers and retrieval diagnostics. - Applying RAG strategies in enterprise AI for domain-specific improvements.…

1
The Power of Synthetic Data | Data Brew | Episode 38 42:28

for 11 weeks siden42:28

42:28

In this episode, Yev Meyer, Chief Scientist at Gretel AI, explores how synthetic data transforms AI and ML by improving data access, quality, privacy, and model training. Highlights include: - Leveraging synthetic data to overcome AI data limitations. - Enhancing model training while mitigating ethical and privacy risks. - Exploring the intersection of computational neuroscience and AI workflows. - Addressing licensing and legal considerations in synthetic data usage. - Unlocking private datasets for broader and safer AI applications.…

1
Secret to Production AI: Tools & Infrastructure | Data Brew | Episode 37 37:14

for 13 weeks siden37:14

37:14

In this episode, Julia Neagu, CEO & co-founder of Quotient AI, explores the challenges of deploying Generative AI and LLMs, focusing on model evaluation, human-in-the-loop systems, and iterative development. Highlights include: - Merging reinforcement learning and unsupervised learning for real-time AI optimization. - Reducing bias in machine learning with fairness and ethical considerations. - Lessons from large-scale AI deployments on scalability and feedback loops. - Automating workflows with AI through successful business examples. - Best practices for managing AI pipelines, from data collection to validation.…

1
Mixture of Memory Experts (MoME) | Data Brew | Episode 36 41:24

for 15 weeks siden41:24

41:24

In this episode, Sharon Zhou, Co-Founder and CEO of Lamini AI, shares her expertise in the world of AI, focusing on fine-tuning models for improved performance and reliability. Highlights include: - The integration of determinism and probabilism for handling unstructured data and user queries effectively. - Proprietary techniques like memory tuning and robust evaluation frameworks to mitigate model inaccuracies and hallucinations. - Lessons learned from deploying AI applications, including insights from GitHub Copilot’s rollout. Connect with Sharon Zhou and Lamini: https://www.linkedin.com/in/zhousharon/ https://x.com/realsharonzhou https://www.lamini.ai/…

1
Mixed Attention & LLM Context | Data Brew | Episode 35 39:11

for 22 weeks siden39:11

39:11

In this episode, Shashank Rajput, Research Scientist at Mosaic and Databricks, explores innovative approaches in large language models (LLMs), with a focus on Retrieval Augmented Generation (RAG) and its impact on improving efficiency and reducing operational costs. Highlights include: - How RAG enhances LLM accuracy by incorporating relevant external documents. - The evolution of attention mechanisms, including mixed attention strategies. - Practical applications of Mamba architectures and their trade-offs with traditional transformers.…

1
Kumo AI & Relational Deep Learning | Data Brew | Episode 34 43:27

for 27 weeks siden43:27

43:27

In this episode, Jure Leskovec, Co-founder of Kumo AI and Professor of Computer Science at Stanford University, discusses Relational Deep Learning (RDL) and its role in automating feature engineering. Highlights include: - How RDL enhances predictive modeling. - Applications in fraud detection and recommendation systems. - The use of graph neural networks to simplify complex data structures.…

1
LLMs: Internals, Hallucinations, and Applications | Data Brew | Episode 33 38:50

for 2 years siden38:50

38:50

Our fifth season dives into large language models (LLMs), from understanding the internals to the risks of using them and everything in between. While we're at it, we'll be enjoying our morning brew. In this session, we interviewed Chengyin Eng (Senior Data Scientist, Databricks), Sam Raymond (Senior Data Scientist, Databricks), and Joseph Bradley (Lead Production Specialist - ML, Databricks) on the best practices around LLM use cases, prompt engineering, and how to adapt MLOps for LLMs (i.e., LLMOps).…

1
Demonstrate–Search–Predict Framework | Data Brew | Episode 32 33:14

for 2 years siden33:14

33:14

We will dive into LLMs for our fifth season, from understanding the internals to the risks of using them and everything in between. While we’re at it, we’ll be enjoying our morning brew. In this session, we interviewed Omar Khattab - Computer Science Ph.D. Student at Stanford, creator of DSP (Demonstrate–Search–Predict Framework), to discuss DSP, common applications, and the future of NLP.…

1
Generative AI Risks | Data Brew | Episode 31 34:38

for 2 years siden34:38

34:38

We will dive into LLMs for our fifth season, from understanding the internals to the risks of using them and everything in between. While we’re at it, we’ll be enjoying our morning brew. In this session, we interviewed Yaron Singer, CEO of Robust Intelligence, Professor of Computer Science at Harvard University, and guest of Data Brew Season 3 (our first repeat guest!). In this session, we discuss generative AI, the trends toward embracing LLMs, and how the surface area for vulnerabilities in generative AI is much bigger.…

1
John Snow Labs & SparkNLP | Data Brew | Episode 30 43:17

for 2 years siden43:17

43:17

We are back and we will dive into LLMs from understanding the internals to the risks of using them and everything in between. While we’re at it, we’ll be enjoying our morning brew. In this session, we interviewed David Talby who is the CTO at John Snow Labs; they help healthcare & life science companies put AI to good use. David's interests include natural language processing, applied artificial intelligence in healthcare, and responsible AI.…

Data Brew by Databricks

1
Data Brew Season 4 Episode 6: Professional Athletes 35:49

for 3 years siden35:49

35:49

For our fourth season, we focus on connected health and how data & AI augment and improve our daily health. While we’re at it, we’ll be enjoying our morning brew. Shayna Powless and Eli Ankou, professional cyclist for L39ion of Los Angeles and defensive tackle for the Buffalo Bills, respectively, provide valuable insight on how professional athletes leverage data to improve their performance and how they combine their passion for sports with the Dreamcatcher Foundation. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 4 Episode 5: Public Health: Education, Access, and Policy 34:39

for 3 years siden34:39

34:39

For our fourth season, we focus on connected health and how data & AI augment and improve our daily health. While we’re at it, we’ll be enjoying our morning brew. Matt Willis, Marin County Public Health Officer, shares the three pillars of public health: education, access, and policy, and the critical role data plays in addressing the COVID-19 pandemic & opioid epidemic. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 4 Episode 4: 1283 Days of Running (and Counting) 35:54

for 3 years siden35:54

35:54

For our fourth season, we focus on connected health and how data & AI augment and improve our daily health. While we’re at it, we’ll be enjoying our morning brew. Running the length of the US every year, Alexandra Matthiesen shares her motivational secrets for running 1,283 consecutive days (and counting!) and redefining physical and mental limits. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 4 Episode 3: Last Man Standing 41:20

for 3 years siden41:20

41:20

For our fourth season, we focus on connected health and how data & AI augment and improve our daily health. While we’re at it, we’ll be enjoying our morning brew. Winner of the infamous Last Man Standing race (running 246 miles in 59 hours), Guillaume merges the world of competitive long-distance running with data science to push the boundaries of body and mind. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 4 Episode 2: NBA Analytics 30:16

for 3 years siden30:16

30:16

For our fourth season, we focus on connected health and how data & AI augment and improve our daily health. While we’re at it, we’ll be enjoying our morning brew. Alexander Powell chronicles the evolution of sports analytics and how professional sports teams use data as a competitive advantage. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 4 Episode 1: Reducing Injury & Increasing Retention of Industrial Athletes 33:58

for 3 years siden33:58

33:58

For our fourth season, we focus on connected health and how data & AI augment and improve our daily health. While we’re at it, we’ll be enjoying our morning brew. Globally, 38,000 people get hurt on the job every hour. In the United States alone, over $250 billion dollars is spent on workplace injury annually. Sean Petterson, founder and CEO of StrongArm Tech, discusses the role of wearable devices to reduce workplace injury and increase retention of industrial athletes. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 3 Episode 6: Open Source 33:49

for 3 years siden33:49

33:49

For our third season, we focus on how leaders use data for change. Whether it’s building data teams or using data as a constructive catalyst, we interview subject matter experts from industry to dive deeper into these topics. For our season 3 finale, Nithya Ruff discusses the open-source ecosystem, ways to contribute to open-source projects (hint: it’s not just about the code), and how businesses can balance community and company interests. With 95% of open-source contributions coming from men, Nithya also educates us on how to improve diversity & inclusion in the open-source community. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 3 Episode 5: Sustainability & Sake 32:26

for 4 years siden32:26

32:26

For our third season, we focus on how leaders use data for change. Whether it’s building data teams or using data as a constructive catalyst, we interview subject matter experts from industry to dive deeper into these topics. We interview Junta Nakai in our most unique location yet - Brooklyn Kura - the first non-Japanese sake distillery in New York. In this episode, Junta shares the philosophical, economic, and tactical approaches to sustainability and ESG, as well as the secrets to brewing sake in the US. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 3 Episode 4: Executive Education 38:46

for 4 years siden38:46

38:46

For our third season, we focus on how leaders use data for change. Whether it’s building data teams or using data as a constructive catalyst, we interview subject matter experts from industry to dive deeper into these topics. Did you know that the average tenure of a board member is longer than the average tenure of a marriage in the United States? In this episode, Coco Brown discusses the benefits and drawbacks of the long tenures of corporate boards, their current structure, the impact of recent legislation, and the importance of executive education to guide you through all of this. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 3 Episode 3: 3 T’s to Securing AI Systems: Tests, tests, and more tests 35:01

for 4 years siden35:01

35:01

For our third season, we focus on how leaders use data for change. Whether it’s building data teams or using data as a constructive catalyst, we interview subject matter experts from industry to dive deeper into these topics. What does it mean to make your machine learning system “production-ready”? Yaron Singer walks us through the infrastructure, testing procedures, and more that help make ML systems ready for the real world in this episode of Data Brew. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 3 Episode 2: Data Culture Outside ‘The Valley’ 35:39

for 4 years siden35:39

35:39

For our third season, we focus on how leaders use data for change. Whether it’s building data teams or using data as a constructive catalyst, we interview subject matter experts from industry to dive deeper into these topics. Have you ever had a spam call automatically blocked for you? You can thank First Orion for that - in one day they blocked or scam tagged over 108 million calls - just on T-Mobile alone! In this episode, we have the pleasure to chat with Charles Morgan and Kent Welch, CEO and CDO, respectively, of First Orion to discuss Arkansan data culture, First Orion’s one hundred day program, and team culture. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 3 Episode 1: Disrupt: Challenge your Business Assumptions 29:45

for 4 years siden29:45

29:45

For our third season, we focus on how leaders use data for change. Whether it’s building data teams or using data as a constructive catalyst, we interview subject matter experts from industry to dive deeper into these topics. In this season opener, Elena Donio shares her experience using data and domain knowledge to disrupt the traditional service and sales compensation model. She also discusses how to build companies that scale, manage corporate cultural evolution, and the influence of corporate boards. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 2 Episode 9: Data Driven Software 31:12

for 4 years siden31:12

31:12

For our second season of Data Brew, we will be focusing on machine learning, from research to production. We will interview folks in academia and industry to discuss topics such as data ethics, production-grade infrastructure for ML, hyperparameter tuning, AutoML, and many more. We branch, version, and test our code, but what if we treated data like code? Tim Hunter joins us to discuss the open-source Data-Driven Software (DDS) package and how it leads to immense gains in collaboration and decreased runtime for data scientists at any organization. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 2 Episode 8: Feature Engineering 31:17

for 4 years siden31:17

31:17

For our second season of Data Brew, we will be focusing on machine learning, from research to production. We will interview folks in academia and industry to discuss topics such as data ethics, production-grade infrastructure for ML, hyperparameter tuning, AutoML, and many more. Is there ever a “one-size fits all” approach for feature engineering? Find out this and more with Amanda Casari and Alice Zheng, co-authors of the Feature Engineering for Machine Learning book. See more at databricks.com/data-brew…

Data Brew by Databricks

1
Data Brew Season 2 Episode 7: Interpretable Machine Learning 37:07

for 4 years siden37:07