Skills

I work at the intersection of computational social science, linguistics, and data science. My technical background includes programming, machine learning, natural language processing, corpus methods, and experimental tools for studying bilingualism. I value reproducible workflows, clean data practices, and accessible, well‑documented research pipelines.

• Programming: Python, R, SQL, LaTeX
• NLP: Hugging Face Transformers, LLM evaluation, prompting, multilingual NLP, embeddings, fastText, keyword spotting
• Machine Learning: fine-tuning, inference, classification, regression, dimensionality reduction (t-SNE), cross-validation
• Libraries: pandas, NumPy, scikit-learn, PyTorch, matplotlib, seaborn, tidyverse, ggplot2, lme4, text2vec, Rtsne
• Tools: Git, GitHub, Jupyter, RStudio, Tableau, Praat, ELAN, Qualtrics
• Document & Writing Tools: Overleaf, Markdown, Zotero
• Russian, English, French, American Sign Language