CV
Contact Information
| Name | Migon Choi |
| Professional Title | Materials Scientist | AI for Materials & Autonomous Experimentation |
| megon98@gmail.com |
Professional Summary
Materials scientist working at the intersection of experimental science, machine learning, uncertainty-aware decision-making, and autonomous experimentation.
Experience
-
2026 - Associate Researcher
Duke University
- Developing data infrastructure and metadata systems.
-
2021 - 2026 Doctoral Researcher
Duke University
- Developed machine-learning approaches for small, noisy, and heterogeneous experimental materials datasets.
- Applied Bayesian modeling, uncertainty quantification, active learning, and interpretable machine learning to materials discovery and experimental decision-making.
- Integrated computational modeling with experimental materials synthesis and characterization.
-
2024 - 2026 Senior Associate
Duke Capital Partners
- Evaluated science- and engineering-driven technologies through technical diligence and venture assessment.
- Assessed technical risk, commercialization potential, and translation from academic research to industry.
-
2020 - 2021 Process Integration Engineer
Samsung Electronics
- Worked on semiconductor process integration for 8/14 nm RF FinFET technologies at Samsung Foundry.
- Collaborated across materials, CVD, photolithography, and device/process characterization.
-
2020 - 2020 Intern
Samsung Electronics
- Completed an industry internship at Samsung Electronics prior to joining Samsung Foundry as a full-time engineer.
-
2020 - 2020 Undergraduate Research Assistant
Korea Institute of Energy Research
- Conducted undergraduate research in energy materials and experimental materials science.
-
2019 - 2019 Undergraduate Research Assistant
Korea Institute of Geoscience and Mineral Resources
- Conducted undergraduate research involving materials processing and resource recovery.
Education
-
2021 - 2026 Ph.D.
Duke University
Materials Science and Engineering
-
2017 - 2020 B.S.
Pusan National University
Materials Science and Engineering
Publications
-
2026 Uncertainty-aware dimensionality prediction of low-dimensional hybrid metal halides by integrating Bayesian modeling and experiments
Journal of Materials Chemistry A
-
2025 P-type Charge Transfer Doping for Mixed Tin-Lead Halide Perovskites: Mo(tfd-COCF3)3 and F4TCNQ
ACS Applied Materials & Interfaces
Skills
Machine Learning: Bayesian modeling, Uncertainty quantification, Active learning, Interpretable machine learning
Scientific Computing & Data: Python, Scientific data pipelines, Data analysis, Statistical modeling, Data curation
Materials Science: Semiconductor materials, Thin-film synthesis, Materials characterization, Halide perovskites
Research Interests: AI for materials, Scientific machine learning, Autonomous experimentation, Decision-making under uncertainty, Materials data systems
Certificates
- AI for Materials - Duke University (2026)
- VC Foundations Workshop - Duke Center for Teaching and Learning (2025)