Machine Learning Researcher · Software Engineer
I’m a machine learning researcher and software engineer. My work focuses on interpretable methods for biomedical data, with broader interests in data-efficient learning, robust evaluation, and the engineering needed to turn ideas into dependable systems.
Selected research
I’m especially interested in ECG representation, interpretable clinical risk, and making better decisions under uncertainty.
BioData Mining · 2026
Can a compact kernel combine angular similarity and distance from a normal reference to classify ECG beats with an inspectable decision geometry?
Health Informatics Journal · 2026
Can hierarchical co-occurrence structure be built into logistic regression while keeping the resulting risk model inspectable?
2025 10th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM) · 2025
How can forecasting, policy learning, and downside-risk control be coordinated for sequential portfolio allocation?
Selected systems
Good research needs reliable experiments, clear data flows, and software built with care. Public artifacts and private professional work are clearly labeled.
Research artifact · Public artifact
The archived computational material associated with the BioData Mining study of angle–distance kernels for ECG classification and anomaly detection.
View projectResearch artifact · Public artifact
The analysis package associated with the Health Informatics Journal study of closure-constrained logistic regression.
View projectProfessional system · Code non-public
Research and engineering work supporting power-network operations and emergency-response workflows.
View projectProfessional system · Code non-public
Backend architecture and performance work for a student and alumni job-networking platform.
View projectResearch map
Across different applications, I keep returning to the same questions: what should a model learn, how should we evaluate it, and how can we make the result easier to trust?
Selected writing
Biomedical AI
A research note on similarity geometry, patient-wise evaluation, and what the QADK study does—and does not—show.
Read noteInterpretable ML
How structured constraints can keep a clinical-risk model inspectable, plus the validation still needed before deployment.
Read noteMethods
A compact explanation of kernels, inductive bias, and why small-data settings still reward careful similarity design.
Read noteContact