Technical session · 2026

Real-Time AI Pipelines at Scale: Embedding LLMs into Apache Beam

Bringing LLM inference and RAG inside the pipeline itself — embedding models directly into Apache Beam transforms so streaming data can reason in real time, delivering low-latency intelligence on high-velocity data without ever leaving the stream.

Event
Apache Beam Summit 2026
Date
June 22, 2026
Where
New York City
Speaker
Samir Sengupta

Bringing LLM inference and RAG inside the pipeline itself — embedding models directly into Apache Beam transforms so streaming data can reason in real time, delivering low-latency intelligence on high-velocity data without ever leaving the stream.

What the talk covers

  • LLM inference is embedded directly inside Apache Beam transforms, so reasoning happens in the stream rather than in a round trip out of it.
  • Retrieval runs inline too — the pipeline carries its own RAG stage instead of calling a separate service per element.
  • Model handles are shared across bundles so a transform does not pay initialisation cost per element, which is what usually makes in-pipeline inference impractical.
  • The result is low-latency intelligence on high-velocity data without the data ever leaving the pipeline.

Why it matters

The usual shape for streaming AI is a pipeline that leaves the stream: batch the events, call an external inference service, wait, come back. Every hop adds latency and a new failure mode.

The other talk

Hiring for AI or ML?

I am open to AI/ML Engineering, Data Science, and Python roles, plus research collaborations and consulting. New York based, shipping worldwide.