CV

General Information

AI Researcher with a focus on LLM Safety, Interpretability and Trust.

Education

• 2025 — Present: Ph.D. in Computer Science — EPFL, Lausanne
• 2023 — 2025: M.S. in Machine Learning (with honors) — HSE University, Moscow
  CGPA 4/4. Thesis: “Self-Improvement for LLM”. Advisors: Irina Nikishina and Chris Biemann.
• 2021 — 2023: Graduate Program in AI and Applied Mathematics (with honors) — MSU, Moscow
  CGPA 3.65/4.
• 2018 — 2022: B.S. in Neuroscience (with honors) — HSE University, Moscow
  CGPA 3.95/4. Thesis: “Advanced Empirical Research on Grapheme-Color Synesthesia Induction With V4 tDCS Stimulation”. Advisors: Oksana Zinchenko and Alexey Gorin.

Work Experience

• 09.2025 — Present: Doctoral Researcher — EPFL, DLab
  • LLM Safety Pretraining
  • Mechanistic Interpretability
• 10.2024 — 09.2025: Research Lead — Skoltech
  • LLM Uncertainty Estimation
  • Hallucinations Detection and Mitigation
  • LLM Safety
• 07.2023 — 10.2024: Research Engineer — Skoltech
  • LLM for Lexical Semantics
  • Machine Translation
  • LLM Efficiency: PEFT and Compression
  • Multivariate Time-Series Unsupervised Learning
• 08.2022 — 06.2023: Intern Researcher — DeepPavlov.ai
  • Image2Text Dialogue System Research

Awards

• 2024: Yandex Scholarship — for exceptional GPA and significant research contributions
• 2024: HSE Academic Scholarship — for outstanding academic performance
• 2024: HSE Best Paper — best student paper award
• 2023: HSE Best Paper — best student paper award

Student Supervision

• Dominic Bazina-Grolinger (2026, EPFL) — MSc project: “Jailbreaking Monitoring with Persona Vectors”
• Wiktoria Rozkosz (2026, EPFL) — MSc project: “Jailbreaking with User-Based Persona”
• Edgar Desnos (2026, EPFL) — MSc project: “Multi-Agent Cooperation Simulations”
• Ekaterina Neminova (2023, HSE) — BSc thesis co-supervision with Irina Nikishina; led to the ACL paper “TaxoLLaMA”
• Alina Lobanova (2023, HSE) — BSc thesis co-supervision with Irina Nikishina; led to the ACL paper “TaxoLLaMA”
• Vladimir Ganzhara (2024, HSE) — MS project: “Aligning LLM Confidence with Truthfulness with Self-Play”
• Gleb Stenin (2024, HSE) — MS project: “Aligning LLM Confidence with Truthfulness with Self-Play”
• Vlad Knyazhevski (2024, HSE) — MS project: “Aligning LLM Confidence with Truthfulness with Self-Play”
• Luiza Nigogosova (2024, HSE) — MS project: “Aligning LLM Confidence with Truthfulness with Self-Play”

Teaching Experience

• 2026: Guest Lecture — Uncertainty Estimation in LLMs, Skoltech NLP, Moscow (Guest Lecturer)
• 2026: Interaction Design (en) — EPFL, Lausanne (Teaching Assistant)
• 2025: Tensor Decomposition for DL (en) — YSDA, Moscow (Lecturer, Seminarian, Homework)
• 2024 — 2025: Neural Natural Language Processing (en) — HSE, Moscow (Lecturer and Seminarian)
• 2023 — 2024: Neural Natural Language Processing (en) — HSE, Moscow (Lecturer, Seminarian, Homework)
• 2024: Tensor Decomposition for DL (en) — Skoltech, Moscow (Lecturer, Seminarian, Homework)
• 2024: Tensor Decomposition for DL (en) — Deep School, Moscow (Lecturer, Seminarian, Homework)

Reviewing

ACL · ICLR · EMNLP · NAACL · NeurIPS · COLING · IEEE · AINL

Additional Education

• 2026: Technical AI Safety — BlueDot
• 2026: AGI Strategy — BlueDot
• Aug 2023: AI Summer School — Skoltech
• Jul 2023: Generative Modeling and RL Summer School — AIRI
• May 2023: Generative Modeling and AI Theory Summer School — HSE
• Feb 2023: Applied Informatics and Mathematics Winter School — HSE
• Jul 2022: NLP and CV Summer School — AIRI
• Aug 2020: Machine Learning and Applied Mathematics Summer School — MIPT and IITP RAS