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

University of Basel; Basel; On-site; CHF 90,000 - 120,000; Part time

Benefits offered by this job

sciCORE access to GPU resources

Relocation support for international/h

International research environment

Job summary

The Digital Humanities Laboratories (DHLabs) at the University of Basel invite applications for a postdoctoral researcher (80%) to start March 1, 2027 or by arrangement. You will lead the computational work for a project on probabilistic texts, fine-tune open-weight models on historical corpora, and contribute to a public benchmark with the team of literary historians and computer scientists.

Requirements include a doctorate in a computational field, hands-on experience with transformers

Qualifications

• Doctoral degree in a computational field with substantial computation
• Hands-on experience training and analyzing transformer models in Python
• Experience with interpretability methods and benchmarking datasets

Responsibilities

• Lead computational work for the project with supervision by PI and collaborators
• Fine-tune open-weight language models on period texts using parameter-efficient methods
• Build the attribution pipeline and validate with SHAP, probing, and causal-interventions
• Run systematic model tests and prompting experiments with literary historians
• Lead or co-author papers and contribute to the benchmark release and related publications

Skills

Transformer models

Python

NLP research

Experiment design

English communication

Education

Doctorate in CS/NLP/ML or related field

Tools

PyTorch

Hugging Face

GPU clusters

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.

We offer you

A position for the duration of the project (48 months at 80%): a first contract of two years, with an extension for the remaining two years expected after a positive review. Residence in the trinational region of Basel for the duration of this project is mandatory. The terms of employment for postdocs follow the guidelines of the University of Basel and the SNSF: SNSF salary ranges and guidelines. The project provides access to sciCORE, the University's scientific computing centre, and its GPU resources. Teaching in the Digital Humanities programme may be arranged. The University of Basel stands for excellence through diversity and is committed to equal opportunities and family friendliness. International applicants are welcome; the Welcome & Euraxess Center supports relocation and permit procedures.