Hello, I'm
ML Engineer & Data Scientist
I build AI systems that turn data into real-world impact — spanning published research and recommendation systems used by millions. Currently building a Decision Intelligence Platform at Ailys.
↳ Based in Seoul — happiest shipping from anywhere with a good view.
I work where messy real-world problems meet machine learning, and I care most about the part that's easy to skip: making a model actually change a decision. These days that's underwriting intelligence at Ailys, where a model is judged by the business outcome it moves — a loss ratio, an approval — not its accuracy on a held-out set.
I've worked across applied ML — recommendation and knowledge tracing used by millions, computer vision on real construction sites, and peptide-identification research I published as first author. The throughline isn't one technique; it's carrying a problem from "no one's framed this yet" to something that ships and holds up in the real world.
My goal is AI that's genuinely useful: systems that turn data into decisions people can trust and act on. I'm going deeper on the fundamentals now, with an eye on building decision systems of my own down the road.
Ailys — Data Scientist
Apr 2025 – Present
Building a Decision Intelligence Platform that helps people and businesses make better decisions.
TmaxEduAI — AI Engineer
Jan 2023 – Nov 2024
Built deep learning models, rule-based algorithms, and MLOps pipelines for knowledge tracing and personalized content recommendation.
Bioinformatics and Intelligent Systems Lab, Hanyang University — Graduate Research Assistant
Aug 2020 – Dec 2022
Designed ML/DL-based post-processing tools for reranking and rescoring to improve peptide identification accuracy in de novo sequencing.
The Construction Systems Laboratory, Inha University — Undergraduate Researcher
Jul 2019 – Feb 2020
Developed image classification and object detection models to detect hazardous objects in indoor construction environments.
NovoRank: Refinement for De Novo Peptide Sequencing Based on Spectral Clustering and Deep Learning
Jangho Seo, Seunghyuk Choi, Eunok Paek — J. Proteome Res. 2025, 24, 2, 903–910
Read paper →Decision Intelligence · Insurance & Lending
Underwriting AI usually just scores accept/reject. On Ailys's DEIN platform I build ML judged by business KPIs — an insurance disease-risk model (PMI-defined targets, recall >93%) feeding loss-ratio simulations, and credit reject inference that expands lending approvals into no-data segments.
Recommendation Systems · Knowledge Tracing
Course recommendations for a 2M+ user platform were generic and didn't reflect learner progress. I built a deep learning recommendation model on sequential interaction data and shipped it through an Airflow pipeline, lifting course enrollment (CVR) by 5% and content completion by 25%.
Bioinformatics · Deep Learning · Clustering
Conventional de novo peptide sequencing tools score spectra in isolation and frequently misidentify peptides. I built a two-step clustering and deep learning re-ranking pipeline that cross-checks candidates against similar spectra, improving precision and recall by an average of 4.6% and 4.5% across three state-of-the-art tools.
Computer Vision · Image Augmentation
Recognizing small hazard objects on construction sites is data-hungry, but labeled images are scarce. I studied which image-augmentation strategies actually help, lifting a CNN's accuracy from 85.7% to 87.6% — and found rotation hurts more than it helps for these objects.
Python, SQL, Java
PyTorch, TensorFlow, scikit-learn, Polars, Airflow, AWS SageMaker
Decision Intelligence (risk & underwriting), Recommendation Systems, Knowledge Tracing, Computer Vision, NLP, Bioinformatics