DES is a property of AIM Media House.
DES is a property of AIM Media House.
Your warehouse got you this far. Your lake promised flexibility. But the future lives in between — the lakehouse.
This workshop tears apart the modern data stack and rebuilds it. You’ll go deep on Delta Lake, Apache Iceberg, ACID transactions, and schema evolution at scale. You’ll discover why semantic layers are quietly becoming the most important piece of the puzzle — turning data chaos into self-service analytics teams actually trust.
And because no data platform in 2026 is complete without AI, we’ll design architectures where feature stores, ML pipelines, and analytics don’t just coexist — they reinforce each other. Bring your SQL skills and curiosity. Leave with a blueprint you can use on Monday.
Your pipelines work — until they don’t. And when they break at 2 AM, nobody knows why.
This workshop fixes that. You’ll learn how to bring real engineering discipline to data — CI/CD, automated testing, version control, and observability applied to pipelines the way software teams have done it for years.
We’ll get hands-on with orchestration frameworks like Airflow and Dagster, build data quality checks that catch issues before your stakeholders do, and implement lineage tracking so you always know what went wrong and where.
We’ll also connect the dots to LLMOps and ML pipelines, because reliable AI starts with reliable data. Bring your Python or SQL chops. Leave with pipelines that don’t page you at midnight.
Everyone’s talking about prompts and models. Nobody’s talking about the pipes feeding them. Here’s the truth — your LLM is only as good as the data infrastructure behind it.
This workshop puts data engineers where they belong: at the center of the AI stack. You’ll build the pipelines that power retrieval-augmented generation — from ingestion and transformation to embedding generation and vector store delivery, using tools you already know like Airflow and dbt.
We’ll tackle the unsexy but essential stuff: dataset versioning, embedding lifecycle management, and keeping knowledge bases fresh so your LLM doesn’t hallucinate last quarter’s answers. Bring your Python or SQL skills and a basic understanding of embeddings. Leave knowing how to build the data backbone that makes AI actually work.
You shipped your LLM app. Congratulations. Now the hard part starts. Because production AI isn’t a launch — it’s a living system that drifts, degrades, and surprises you in ways traditional monitoring never prepared you for.
This workshop is about what happens after deployment. You’ll learn to instrument the full pipeline — prompt telemetry, retrieval accuracy, embedding quality, and model output evaluation — using tools like LangSmith and Weights & Biases. We’ll dig into the problems nobody warns you about: dataset drift, prompt regressions, and retrieval pipelines that silently rot.
Most importantly, you’ll build automated feedback loops that don’t just detect issues but make your system smarter over time. Bring experience with AI pipelines and monitoring tools. Leave with the operational playbook that keeps your LLM reliable long after the demo hype fades.
