MLOps World: Machine Learning in Production Courses

Reward Function As A Service: A Relatively Easy Recipe for Training Your Own Reasoning Model

Discover a template for post-training Deepseek-style LLMs with custom reward functions, allowing model customization for domains that can be evaluated programmatically through Python functions.

• YouTube
• 35 minutes
• Self-Paced
• Free Video

Building a Deep Research with Open-Source - Understanding Modern Research Agents

Explore the concepts behind modern research agents by examining an open-source clone of OpenAI's Deep Research, with insights from Stefan Webb on how this technology synthesizes diverse information.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Teaching AI to Reason: Reinforcement Fine-Tuning for Multi-Turn Agentic Workflows

Discover how reinforcement fine-tuning enables more reliable LLM performance in complex agentic tasks by defining reward functions that shape model behavior across multiple turns, reducing costs while improving precision.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Beyond Gemini: Using Reinforcement Learning to Unlock Reliable AI Agents with Open LLMs

Explore how reinforcement learning enables fine-tuning open-source LLMs to create AI agents that outperform larger models like Gemini, featuring techniques like agentic RAG and self-play for educational applications.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Beyond Benchmarks: Rethinking How We Evaluate LLMs in High-Stakes Environments

Explore the challenges of evaluating LLMs in critical applications, from factual accuracy to ethical alignment, and learn about compositional quality tuning frameworks that balance trade-offs between different evaluation dimensions.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

All the Flavors of AI-powered Search

Explore the evolution of AI-powered search, from basic vector search to advanced multivector representations like ColPali, and understand its crucial role in RAG systems for improved AI responses.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Closing the Reliability Gap: Practical Strategies with Guarantees for Trustworthy GenAI

Explore practical strategies for improving GenAI reliability in production systems, from identifying factual errors to implementing remediation techniques that create trustworthy AI systems requiring minimal human oversight.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Workflows Then Agents: The Practical Approach to Enterprise AI

Discover how to build reliable LLM workflows that solve real business problems before diving into complex agent architectures for practical enterprise AI implementation.

• YouTube
• 35 minutes
• Self-Paced
• Free Video

Using LLMs for Data Imputation

Explore how Large Language Models enhance data imputation accuracy in recommender systems, comparing LLM methods against traditional approaches across varying missing data scenarios.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

Navigating AI Compliance - ISO 42001, the EU AI Act, and the Future of Regulated AI

Explore AI governance frameworks including ISO 42001 and EU AI Act, covering compliance strategies, risk management, and regulatory best practices for deploying AI in regulated industries.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

From One Voice to Forty - Inside Vimeo's Dubbing Engine

Discover how Vimeo built an AI-powered dubbing engine that transforms single videos into multilingual content with real-time translation, precise timing, and natural-sounding audio.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

A Modular Multimodal LLM Framework for Disease Prediction

Discover how to build a modular multimodal LLM framework that integrates EHR and wearable data for disease prediction, achieving superior performance over single-modality baselines.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

LLMOps Infrastructure for Production-Grade Agentic RAG Applications with Union.ai

Master LLMOps infrastructure for production-grade agentic RAG applications using Union.ai platform, covering deployment, iteration, and best practices for maintaining AI systems.

• YouTube
• 1 hour 22 minutes
• Self-Paced
• Free Video

Scaling Down, Powering Up - Can Efficient Training Beat Scaling Laws?

Explore data-centric and model-centric strategies for training efficient language models, including small LMs, data filtering, pruning, distillation, and quantization techniques.

• YouTube
• 1 hour 9 minutes
• Self-Paced
• Free Video

Optimized RAG - Strategies for Cost and Scale

Master cost-effective RAG deployment strategies from prototype to production, covering embedding quantization, context compression, and ranking techniques with hands-on Python implementation.

• YouTube
• 1 hour 27 minutes
• Self-Paced
• Free Video