Postdoctoral Researcher (80%) in Language Model Interpretability and Digital Humanities

Universität Basel; Basel; On-site; CHF 90,000 - 130,000; Part time

Job summary

University of Basel's Digital Humanities Laboratories invites applications for a postdoctoral researcher (80%) in contralab. You will lead computational work, fine-tune open-weight models on eighteenth-century texts, and co-author papers with linguists and historians.

You will work under Prof. Dhaliwal and collaborate with Dr. Juan Luis Gastaldi, contributing to a public benchmark, datasets, and open science practices. This role supports your research trajectory.

Qualifications

• A doctorate by appointment in computer science, NLP or related field with computational component.
• Hands-on experience training and fine-tuning transformer language models (Python, PyTorch, Hugging Face).
• Experience with interpretability methods and building evaluation datasets/benchmarks.
• Experience designing experiments with proper controls and reproducible research practices.

Responsibilities

• Lead computational work for the project, co-supervised by PI and partner.
• Fine-tune open-weight language models on period texts (LoRA,continued pretraining).
• Build the attribution pipeline with SHAP checks against probing methods.
• Run systematic model tests and prompting experiments with historians.
• Lead the benchmark release (documentation, baselines, public leaderboard).
• Co-author papers for NLP/ML venues and humanities publications.

Skills

Python

NLP

Transformer models

LoRA

Statistical methods

Reproducible research

Education

PhD in CS/NLP/ML/Computational humanities

Tools

GPU clusters

Hugging Face Transformers

Python tooling

Job description

The Digital Humanities Laboratories (DHLabs) at the University of Basel are an interdisciplinary unit for research, teaching and infrastructure on technological and digital worlds in the humanities and social sciences. Within the DHLabs, contralab, the research group of Prof. Dr. Ranjodh Singh Dhaliwal, brings together machine learning and NLP, literary history and theory, media studies and STS, and the philosophy of language. For the four-year project "A Philology of Probabilistic Texts: The Problem of Interpretation in Artificial Intelligence", funded by the Swiss National Science Foundation, contralab is looking for a postdoctoral researcher (80%) as of 1 March 2027 or by arrangement. The project asks what large language models do to meaning when they read historical texts: it maps how eighteenth-century concepts shift across genres and decades in large historical corpora, examines how fine-tuned open-weight models represent those concepts, and releases an annotated corpus of model divergences, an open benchmark for diachronic semantic understanding, and a taxonomy of the ways models misread historical texts. Full details of the project, team and position are available on the contralab website.

Your position

You will lead the project's computational work, co-supervised by the PI and the project partner Dr. Juan Luis Gastaldi (Sorbonne University and ETH Zürich). Your tasks include:

• preparing and validating the historical corpora (OCR quality, genre and date metadata) with the project's research assistant
• fine-tuning open-weight language models on period texts (continued pretraining with parameter-efficient methods such as LoRA)
• building the attribution pipeline, with token-level SHAP checked against probing and causal-intervention methods
• running systematic model tests and controlled prompting experiments with the team's literary historians
• leading the technical side of the benchmark release (documentation, baselines, public leaderboard)
• leading or co-authoring papers at NLP and machine-learning venues and co-authoring the project's humanities publications

The position supports your own research profile and further academic qualification.

Your profile

• A doctorate (by the time of appointment) in computer science, NLP or computational linguistics, machine learning, digital or computational humanities, or a related field with a substantial computational component
• Hands-on experience training, fine-tuning and analysing transformer language models in Python (PyTorch, Hugging Face), including on GPU clusters
• Experience with interpretability methods (feature attribution, probing, activation patching, sparse autoencoders) and/or with building evaluation datasets and benchmarks
• Experience designing experiments with proper controls, baselines and statistical care, and reproducible research-software practice
• A serious interest in historical texts, literary theory and the philosophy of language, and in reading model outputs closely alongside literary historians
• Strong English; knowledge of German is welcome

Desirable: experience with historical or OCR-derived text or semantic change detection; annotation studies; released datasets or open-source tools; publications in NLP or ML venues; engagement with literary theory, historical materialism, hermeneutics, or structuralist or historical linguistics.