DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
Explore DSPy Assertions for enhancing language model pipelines with computational constraints, enabling more reliable and accurate systems through automatic prompt optimization and self-refinement.
Leading Enterprise Data Teams - Strategies for Success
Gain insights on leading enterprise data teams, prioritizing relationships, and effective communication in MLOps. Learn pragmatic strategies for project prioritization and navigating data-driven initiatives to success.
Handling Multi-Terabyte LLM Checkpoints - MLOps Podcast #228
Explore techniques for handling multi-terabyte LLM checkpoints, including storage options, saving and loading strategies, and infrastructure considerations for large-scale AI model training.
FedML Nexus AI: Generative AI Platform at Scale - MLOps Podcast #230
Explore FedML Nexus AI, a scalable platform for building and commercializing generative AI applications. Learn about enterprise AI, model deployment, federated learning, and secure, privacy-preserving machine learning.
RecSys at Spotify - Building and Evaluating Large-Scale Recommender Systems
Explore Spotify's large-scale recommender systems, foundational embeddings for transfer learning, evaluation methods, and MLOps challenges with Senior ML Engineer Sanket Gupta.
Retrieval Augmented Generation - Techniques and Applications
Explore Retrieval Augmented Generation with Syed Asad. Dive into production issues, embedding models, inference layer experiments, and the evolving landscape of AI engineering in this insightful discussion.
Open Standards Make MLOps Easier and Silos Harder - MLOps Podcast Episode 234
Explore open standards in MLOps for easier data system integration, scalability, and collaboration. Learn about Ibis, Apache Arrow, and their impact on data engineering and machine learning workflows.
Ghostwriter - AI Writing That Learns From You
Explore AI-powered email writing that mimics your style and content. Learn how Ghostwriter learns from your past to create personalized, relevant emails effortlessly.
Build Reliable Systems with Chaos Engineering - MLOps Podcast #237
Explore chaos engineering to build reliable systems under unpredictable conditions. Learn benefits, trends, and integration with ML systems for improved resilience and observability.
AWS Trainium and Inferentia - Enhancing AI Performance and Cost Efficiency
Explore AWS Trainium and Inferentia's AI accelerators for enhanced performance, cost savings, and seamless integration with popular frameworks. Learn about their benefits and implementation in ML workflows.
Uber's Michelangelo: Strategic AI Overhaul and Impact - MLOps Podcast
Explore Uber's Michelangelo platform evolution, from basic ML predictions to advanced deep learning and generative AI, addressing challenges and introducing innovative features for streamlined AI operations.
From Robotics to Recommender Systems - MLOps Podcast #240
Explore robotics, computer vision, and recommender systems with Miguel Fierro. Gain insights on ML applications, sports analytics, and AI integration in various fields from a Microsoft Principal Data Science Manager.
Building Production-Ready AI Models for Manufacturing - LatticeFlow Roundtable
Explore production-ready AI models for manufacturing with industry experts. Uncover solutions to data challenges, model failures, and integration issues for robust, safe AI systems.
Navigating the AI Frontier: The Power of Synthetic Data and Agent Evaluations in LLM Development
Explore synthetic data and agent evaluations in LLM development. Learn strategies for enhancing model behavior, prototyping, testing, and fine-tuning to build robust AI applications.
Fresh Data and Smart Retrieval: Milvus and Jina CLIP Explained - MLOps Mini Summit 7
Explore vector database updates, Milvus mechanics, and Jina CLIP's novel multi-task contrastive training for enhanced multimodal and text-based retrieval systems. Master data freshness in high-throughput, low-latency scenarios.
Accelerating Multimodal AI - From Tabular ML to Generative Video Systems
Explore challenges and solutions in multimodal AI, from data management to efficient inference. Learn about systems supporting research and productionization in generative video and language models.
AI Agents for Consumers - The Future of AI and Consumer Empowerment
Explore RealChar's Rivia, an AI application leveraging generative AI and machine learning to handle mundane calls and customer service, freeing human time for meaningful tasks. Gain insights on AI challenges and future prospects.
Why Data Scientists Should Learn Software Engineering Principles
Learn essential software engineering principles for data scientists to improve code quality, modularity, and readability. Enhance project scalability and model deployment capabilities.
AI for Good - Detecting Harmful Content at Scale
Explore AI-driven strategies for detecting harmful online content at scale, optimizing speed and accuracy while addressing cultural sensitivities and evolving challenges in content moderation.
AI Operations Without Fundamental Engineering Discipline - MLOps Podcast #250
Explore the anti-AI hype trend and learn how to bridge the gap between management and tech for effective AI implementation. Gain insights on balancing engineering fundamentals with AI initiatives.
Reliable LLM Products Fueled by Feedback - MLOps Podcast #251
Explore user-centric approaches for reliable LLM products. Learn to convert feedback into actionable insights, analyze root causes, and optimize AI solutions for real-world deployment across various industries.