What You Will Learn

Module 1

Foundations: From Embeddings to Transformers

How machines represent meaning as geometry, and how the Transformer architecture learns to attend, predict, and scale. The conceptual bedrock everything else builds on.

Module 2

From Models to Tools

Post-training alignment (SFT, RLHF, DPO), prompting strategies from zero-shot to chain-of-thought, and how to evaluate and choose between models for your research questions.

Module 3

Deploying for Research

Fine-tuning with LoRA, serving models with vLLM and APIs, and building rigorous text classification pipelines with proper validation.

Module 4

Social Science Applications

Information extraction and RAG pipelines for working with large corpora, plus using LLMs as simulated agents to study human behavior, and when to trust the results.

Module 5

Agentic Workflows

Building autonomous research agents with tool use, ReAct patterns, and multi-step orchestration: the frontier of what LLMs can do for your research pipeline.

Prerequisites

Beginner-to-intermediate Python. A Google account for Colab. No prior deep learning or NLP experience required; we build from fundamentals.

Preliminary notebooks →

Materials

All exercises are open-source Jupyter notebooks. Clone the repo, open in Colab, and follow along.

GitHub Repository →

Begin the Course

Start with Module 1: the mathematical and conceptual foundations that everything else builds on.

Begin →

2026 Dates & Locations

Upcoming

Oxford

March 23–27, 2026
5-day intensive. DPIR, University of Oxford.

ESSCA Paris

April 7, 2026
1-day workshop.

EUI Florence

April 20–21, 2026
2-day workshop. European University Institute.