Mikhail Samoilov

Data Science & ML Engineering

Yandex Search / Trust & Safety

Moscow

A pale sphynx cat sleeping on a windowsill in front of a dark blue night city

Work

Data Scientist

Yandex Search / Antispam

Dates
Feb 2025 — present
Location
Moscow

Working on search antispam systems across the ML product lifecycle — from problem framing and experimentation to production integration.

  • Train and integrate models for spam, harmful content, and fraudulent activity.
  • Automate crowdsourced labeling workflows and reduce labeling costs.
  • Conduct technical interviews for analytics and Python roles.

Education

  1. MIPT logo

    2022 — 2024

    MIPT, Biophysics

    Undergraduate studies

  2. ROSBIOTECH logo

    2024 — 2026

    ROSBIOTECH, Computer Science

    Bachelor's degree

  3. MEPhI logo

    2026 — 2028

    MEPhI, Computer Science

    Machine Learning track

Open Source

Open-source work
across Polars and PyTorch.

github.com/Samoilov2004

Technologies

Machine Learning & AI

  • PyTorch
  • Lightning
  • scikit-learn
  • CatBoost
  • Optuna
  • Hugging Face

LLMs & Generative AI

  • Claude
  • Codex
  • LangChain
  • Transformers
  • RAG
  • Hugging Face

Data Science

  • NumPy
  • Pandas
  • Polars
  • SciPy
  • Statsmodels
  • Plotly

Data Engineering

  • Spark
  • Kafka
  • Airflow
  • Tableau
  • DataLens
  • Selenium

Infrastructure

  • Git
  • Docker
  • PostgreSQL
  • ClickHouse
  • Redis
  • Elasticsearch

Languages

  • Python
  • SQL
  • R
  • C
  • C++
  • Bash

Let's connect!

Find me around the web or send a message.