Print and Probability Research Associate - Dietrich College

Carnegie Mellon University is a private, global research university that challenges the curious and hardworking to deliver work that matters. Our outstanding institution has distinctive areas of excellence and a culture marked by ambition and a deep, practical engagement with challenges facing society. We continue to produce versatile alumni and draw faculty and staff eager to be a part of the university’s creative, dedicated and close-knit community. We place emphasis on practical problem solving, interdisciplinary learning, a transformative spirit, and collaboration.

From creative writing to statistics and data science, behavioral economics to social and political history, Dietrich College is home to 11 humanities and sciences departments, programs and institutes. Our world-class faculty and students work across areas to investigate and solve real-world problems.

The Print & Probability project seeks a Research Associate to develop AI methods for identifying printers of anonymous early modern books (1450-1800). Building on successful prior work that's identified clandestine printers of famous works such as Milton's Areopagitica, Hobbes' Leviathan, Locke's Two Treatises and Spinoza's Theological-Political Treatise, this Schmidt Sciences-funded phase integrates large language models with computer vision to systematically uncover hidden networks of controversial printing during censorship.

Core responsibilities include:

• Develop LLM-driven knowledge graphs that construct probabilistic historical priors from bibliographic records, trial transcripts, censorship lists, and apprenticeship data

• Design agentic frameworks using In-Context Learning and Chain-of-Thought prompting for transparent historical inference

• Develop Historical Hypotheses in collaboration with (other) expert humanists and book historians

• Integrate top-down LLM hypotheses with established bottom-up vision pipeline (existing: dhSegment/Eynollah line extraction, damage detection models, 280M+ character image database)

• Assist in original research on clandestine printing networks using computational tools

• Contribute to publications in both AI and humanities venues (machine learning conferences and book history journals)

• Contribute to open-source tools and datasets for the research community

• Other duties as assigned

Adaptability, excellence, and passion are vital qualities within Carnegie Mellon University. We are in search of a team member who can effectively interact with a varied population of internal and external partners at a high level of integrity. We are looking for someone who shares our values and who will support the mission of the university through their work.

Qualifications:

• Master's degree required

• 1-3 years of research experience required

• Demonstrated expertise with large language models (fine-tuning, prompting, deployment)

• Strong Python programming with deep learning frameworks (PyTorch, TensorFlow)

• Experience with unstructured historical data (text extraction, entity resolution, knowledge graphs)

• Excellent communication skills and commitment to interdisciplinary collaboration

• Evidence of scholarly productivity (publications, presentations, software)

• A combination of education and relevant experience from which comparable knowledge is demonstrated may be considered.

Preferred Qualifications:

• Knowledge of early modern European history (1450-1800) or book history

• Experience with historical bibliography or archival research

• Familiarity with computer vision for document analysis

• Multilingual reading ability (e.g., English, Latin, French, Spanish, Italian, Dutch)

• Publication record in digital humanities or computational social science

Additional Information:

• Sponsorship: Applicants for this position must be currently legally authorized to work for CMU in the United States. CMU will not sponsor or take over the sponsorship of an employment visa for this opportunity.  Carnegie Mellon is not a qualifying employer for the STEM OPT benefit: only the 12-month OPT may be used to work at Carnegie Mellon.

Joining the CMU team opens the door to an array of exceptional benefits.

Benefits eligible emplo