Data For Science

LLM training your engineers will actually use on Monday

Hands-on workshops for engineering, data, and product teams, taught by the instructor behind 170+ live sessions for O’Reilly, Pearson, and Packt since 2019. No slideware tours: your team builds a RAG pipeline, an eval harness, or an agent during the session, on patterns they can carry straight into your codebase.

  • 170+ live sessions

    For O’Reilly, Pearson, and Packt since 2019 — the same format, refined over hundreds of rooms of working engineers.

  • 50+ distinct courses

    From probability and time series to production evals, Graph RAG, and multi-agent systems — depth across the whole stack, not one slide deck.

  • 3,000+ weekly readers

    The Data Science Briefing, 340+ issues since 2019 — the curriculum stays current because the reading never stops.

Formats

  • Live online

    Interactive remote sessions with exercises, live coding, and Q&A — the format Bruno has run for O’Reilly, Pearson, and Packt since 2019.

  • On-site or in-person

    Deep dives tailored to your stack and your use-cases, working with your data where it can be used.

  • Blended

    Pre-work, workshop, and follow-up office hours, so what was learned actually lands in your codebase.

    1. Pre-work
    2. Workshop
    3. Follow-up office hours

    Lands in your codebase

    Fig. 1. The blended format, in order. Segment lengths are not to scale.

What we teach

Every topic below comes from a course Bruno already teaches publicly, or from code we have published. Private sessions take the same material and point it at your systems.

Training topics and what each covers
Topic What it covers
LLMs in production RAG, evaluation, monitoring, cost and latency, and deployment patterns — drawn from the Live LLM Engineering Masterclass: Production Evals, RAG, Agents & LLMOps.
Evaluation that holds up Building a production-grade eval harness, putting error bars on LLM metrics, and eval gates that stop bad merges before they ship.
Agentic workflows Tool use, planning, multi-agent systems with CrewAI, MCP servers from scratch, and containing the ways agents fail.
Working with the APIs OpenAI and Claude APIs for Python developers, LangChain pipelines, Graph RAG with knowledge graphs, and AI-assisted development that survives code review.

O’Reilly Live Training

Bruno teaches regularly on the O’Reilly platform — upcoming public sessions are on the events page. Want the same material tailored to your team, your stack, and your data? That is what the private format is for.

Tell us what your team needs to ship.

Thirty minutes to pick the topics, the format, and the depth — and leave with a proposed outline.

Discuss training

Or email info@data4sci.com