# Bulat Nutfullin

> Machine learning engineer and researcher in LLM and agent security. Builds infrastructure for LLM agents — runtimes, harnesses, tracing, and long-term memory — and researches their security. PhD candidate at the Department of Information Security, Faculty of Computational Mathematics and Cybernetics, Moscow State University (expected 2027).

This is a plain-markdown version of https://nutfullin.com/ for LLM agents and other tools.

- Website: https://nutfullin.com/
- Google Scholar: https://scholar.google.com/citations?user=pl5S66QAAAAJ
- Telegram: https://t.me/Bnutfull

## Research

Prompt-injection attacks and defenses, trojan/backdoor detection in neural networks, uncertainty-aware evaluation of vision-language models. Dissertation: adaptive defense methods for multimodal LLMs at inference — the MARS framework (adaptive routing of inference-time defenses). Also collaborates on computer-vision and statistical methods for forest ecology.

## Selected publications

- V. Kostumov, B. Nutfullin, O. Pilipenko, E. Ilyushin. [Uncertainty-Aware Evaluation for Vision-Language Models](https://arxiv.org/abs/2402.14418). arXiv:2402.14418, 2024.
- D. Khomsky, N. Maloyan, B. Nutfullin. Prompt Injection Attacks in Defended Systems. DCCN, 2024.
- N. Maloyan, E. Verma, B. Nutfullin, B. Ashinov. [Trojan Detection in Large Language Models: Insights from the Trojan Detection Challenge](https://arxiv.org/abs/2404.13660). arXiv:2404.13660, 2024.
- V. A. Evgrafov, B. M. Nutfullin, D. E. Namiot. Attack Methods and Defenses in LLM-Based Agentic Systems. IJOIT 14(5), 2026.
- N. Maloyan, B. Nutfullin, E. Ilyushin. [Dialog-22 RuATD: Generated Text Detection](https://arxiv.org/abs/2206.08029). arXiv:2206.08029, 2022.
- A. E. Bykanov, G. V. Danilov, V. V. Kostumov, O. G. Pilipenko, B. M. Nutfullin, et al. Artificial Intelligence Technologies in the Microsurgical Operating Room. Sovremennye Tehnologii v Medicine 15(2), 2023.

## Experience

- **ML Engineer — AI startup (2024 – present).** Building the runtime that LLM agents run on: agent runner and context management (core contributor); tracing tool for inspecting and debugging agent runs; small decision models for quick yes/no calls (rolling out); document parser from scratch (PDF, DWG and more); long-term memory for agents; meeting transcription with speaker labels.
- **Viasat — ML Engineer (2021 – Jul 2024).** Computer vision and generative ML for a streaming platform: automatic video highlighting, face replacement for actor substitution, and personalized poster generation with Stable Diffusion. Built low-latency online and offline recommendation serving on ClickHouse.
- **Forest ecology — research collaboration (2022 – present).** Statistical testing of tree-species co-occurrence hypotheses and species-compatibility metrics.
- **Forest ecology — startup (2018 – 2022).** 3D point-cloud and remote-sensing CV: tree classification and mistletoe detection from lidar point clouds, satellite-imagery analysis, and geometric registration of field-survey and lidar maps.
- **SAS — Intern (Summer 2019).** Sales-data analytics; benchmarked open-source vs. proprietary ML toolchains.

## Education

- **PhD Candidate (Cand. of Technical Sciences), Computer Science (2021 – present, expected 2027).** MSU, Faculty of Computational Mathematics and Cybernetics — Department of Information Security.
- **MSc, Computer Science (2019 – 2021).** MSU, Faculty of Computational Mathematics and Cybernetics, Dept. of Open Information Technology. Thesis: automatic speaker diarization methods.
- **BSc, Computer Engineering Technology (2015 – 2019).**

## Skills

- Languages: Python, SQL
- LLM / Agents: agentic runtimes, long-term memory, agent tracing, prompt-injection & robustness evaluation
- ML / Data: PyTorch, XGBoost
- Backend / Infra: FastAPI, Temporal, Docker, AWS, git
- Databases: PostgreSQL, ClickHouse, SQLite