"A robot may not injure a human being or, through inaction, allow a human being to come to harm." — Isaac Asimov, First Law of Robotics
PhD student at Tallinn University researching Human-Computer Interaction, deep learning, and affective computing—teaching machines to understand human emotions.
Before research, I spent years building distributed systems, microservices, and cloud-native apps. Functional programming enthusiast who believes elegant code can change how we think about problems.
- As Applied Researcher in Microsoft I work on optimizing NDA'ed AI tools for users
- As PhD student, my research topic is related to neuro-symbolic AI, deep learning and deep knowledge tracing. I work as a part of EduHAI research team
Contributor to scikit-learn — the Python machine learning library. Merged PRs include performance improvements to MultiLabelBinarizer and estimator validation checks.
For example:
- scikit-learn/scikit-learn#12116 — Cache class mapping in MultiLabelBinarizer (performance enhancement)
- scikit-learn/scikit-learn#7846 — Add check for estimator: parameters not modified by fit
- scikit-learn/scikit-learn#7553 — Ensure estimator dict is unmodified by predict/transform
- Hacker News Semantic Search — Semantic search for 38.8M HN items using FAISS & sentence embeddings
- Heartbeat — Remote photoplethysmography: measuring heart rate from facial video
- Google Scholar Save — Export Google Scholar search results to CSV
- GitKot — TikTok-style interface to explore GitHub repositories
- Podcast Whisperer — Making podcasts available in multiple languages
- Azure Terraform — Hetzner cloud automation with Terraform
Elixir experiments • LeetCode solutions • and 176+ more repos
