Christina X Ji

I am a visiting assistant professor in the computer science department at Hamilton College. I currently teach artificial intelligence and labs for introductory programming. My teaching philosophy is to design well-structured courses with in-class problem solving sessions to help students develop hands-on skills they can apply to real-world problems.

My research aims to build AI tools that can serve as collaborators for drug discovery and medical decision-making. Towards this goal, I recently released a preprint on a graph neural network that provides per-atom attributions to explain how the model arrived at its predictions of pharmacokinetic properties of small molecule drugs. My PhD work was focused on building machine learning models to analyze variation in treatment practices across doctors and changes in healthcare over time so that we can better support medical decision-making.

Building a welcoming community is important to me. I organized visit days and orientation for the MIT EECS PhD program, helped with undergraduate orientation, advised first-year undergraduates including first-generation students, and mentored students on their PhD applications. I also earned a teaching certificate from MIT's teaching and learning lab to improve my pedagogical practices.

Before coming to Hamilton, I was a senior machine learning research engineer at Genesis Molecular AI. Genesis builds machine learning models to aid in the drug discovery process. I worked at the cross-functional interface facilitating the application of our models in drug discovery programs. Check out the technical report we released on Pearl, a foundation model for 3D protein-ligand structure prediction!

If you are a Hamilton student, please email me at cji at hamilton dot edu. Otherwise, I can be reached on LinkedIn or at cji at alum dot mit dot edu.

Education

Ph.D. Computer science. Massachusetts Institute of Technology. Minor in biology.
M.Eng. Computer science. Massachusetts Institute of Technology.
B.S. Computer science. Massachusetts Institute of Technology. Minor in mathematics.

Teaching

Artificial intelligence (Hamilton CS375)
Instructor. Fall 2026.

Computer science for all (Hamilton CS101)
Lab instructor. Fall 2026. 2 sections.

Introduction to statistical hypothesis testing (MIT 6.S098)
Creator and instructor. Independent activities period (January) 2024.
[syllabus] [session 1 exercises]

Introduction to statistical data analysis (MIT 6.3720)
Teaching assistant. Spring 2023.
Guest lecturer. Causal inference. May 2023 and May 2024.
[slides] [notes]

Introduction to machine learning (MIT 6.036)
Lab assistant. Spring 2018.

Teaching and Mentoring Awards

Carlton E. Tucker award for teaching excellence. MIT EECS. 2024.
Graduate student extraordinary teaching and mentoring award. MIT School of Engineering. 2024.
Featured associate advisor. MIT Office of the First Year. May 2019.

Theses

Characterizing variation in healthcare across time and providers using machine learning
PhD thesis. 2024.
[thesis]

Modeling progression of Parkinson's disease
MEng thesis. 2019.
[thesis] [code]

Papers

Large-scale study of temporal shift in health insurance claims
Christina X Ji, Ahmed M Alaa, and David Sontag.
Oral spotlight at Conference on Health, Inference, and Learning (CHIL) 2023.
[paper] [poster] [code]

Finding regions of heterogeneity in decision-making via expected conditional covariance
Justin Lim*, Christina X Ji*, Michael Oberst*, Saul Blecker, Leora Horwitz, and David Sontag. *equal contribution
Neural information processing systems (NeurIPS) 2021.
[paper] [poster] [code]

Trajectory inspection: A method for iterative clinician-driven design of reinforcement learning studies
Christina X Ji*, Michael Oberst*, Sanjat Kanjilal, and David Sontag. *equal contribution
American medical informatics association (AMIA) 2021 virtual informatics summit.
[paper] [code]

Preprints

MolLedger: An additive graph neural network with chemically grounded ADME attributions
Christina X Ji.
arxiv. 2026. Submitted for review.
[paper] [code]

Pearl: A foundation model for placing every atom in the right location
Genesis Research Team et al.
arxiv. 2025.
[paper]

Variation in first-line type 2 diabetes treatment due to eGFR and provider preferences: A novel statistical analysis
Christina X Ji, Saul Blecker, Michael Oberst, Ming-Chieh Shih, Leora I Horwitz, and David Sontag.
medrxiv. 2024.
[paper] [code]

Seq-to-final: A benchmark for tuning from sequential distributions to a final time point
Christina X Ji, Ahmed M Alaa, and David Sontag.
arxiv. 2024.
[paper] [code]