Helping large language models understand the world a bit better. I build and adapt tokenizers, fine-tune multimodal models, and streamline LLM pipelines for production-grade use.
- Quick highlights
- Recent experience
- Projects you can try right now
- Publications & research
- How to reach me
- Research Intern at Mohamed bin Zayed University of Artificial Intelligence (Jun 2025 – present) exploring alternative tokenization methods and preparing publication-ready research.
- Middle NLP Engineer at DeepPavlov (May 2025 – present) driving R&D, benchmarking LLMs, and working with GPU stacks from diverse vendors.
- Previously at Center for Applied AI (Skolkovo), Higher School of Economics, Moscow Aviation Institute, and Innopolis University, shipping tokenizer tooling, fine-tuning Qwen and Llama models, and deploying NLP services.
- Active open-source maintainer of tokenizer tooling.
NLP & Deep Learning Stack
DevOps & Tooling
Backend & Communication
Languages & soft skills
- English (proficient)
- Russian (native)
- Flexibility · Responsibility · Curiosity
Research Intern · MBZUAI — Abu Dhabi, UAE (Jun 2025 – present)
- Design and evaluate alternative tokenization strategies for LLM inference.
- Author an academic paper on tokenizer-driven performance gains.
Middle NLP Engineer · DeepPavlov — Moscow, Russia (May 2025 – present)
- Running R&D initiatives and evaluation workflows.
- Running comparative testing on GPU infrastructures from Chinese manufacturers.
Middle NLP Engineer · Center for Applied AI, Skolkovo — Moscow, Russia (Feb 2025 – May 2025)
- Tuned the Qwen2.5-VL model and built supporting pipelines.
- Designed prompting strategies to generate actionable feedback on heterogeneous specifications.
NLP Researcher · Higher School of Economics — Moscow, Russia (Jun 2024 – May 2025)
- Fine-tuned Llama3-8B-Instruct for Russian-language tasks.
- Developed a Russian BPE tokenizer and tooling to manipulate existing vocabularies safely.
- Built a grammar benchmark suite to quantify improvements across downstream tasks.
ML / Backend Engineer · Moscow Aviation Institute — Moscow, Russia (Jul 2023 – Oct 2023)
- Delivered a sentence theme classifier and optimized database queries.
- Integrated Telegram-based interfaces for model delivery.
NLP Engineer · Innopolis University — Innopolis, Russia (Jun 2023 – Jul 2023)
- Developed a deep-learning sentiment model for YouTube comments.
- Fine-tuned BERT for domain-specific tone classification.
Rethinking Tokenization — EACL 2026 (under review)
Researcher & writer, 2025. Investigates how alternative tokenizations of the same text impact LLM inference quality.
TokenSubstitution — ACL 2026 (in progress)
Proposes cost-effective adaptation approach for improving the performance of LLM generation in target language.
Multi-Aspect Tokenizer Evaluation — Russian AI Journey 2025 (accepted)
Demonstrates tokenizer adaptation as a cost-effective technique by analyzing text quality and token efficiency across diverse benchmarks
CRUD Calendar LLM Chatbot — Telegram assistant
- Features: calendar CRUD, summarise latest news, voice reminders.
- Stack: Telegram Bot API, FastAPI, RAG pipeline with Qwen2.5-VL.
Innopolis University — B.S. in Data Analysis & Artificial Intelligence (2022 – 2026)
Key coursework: Software Systems Analysis and Design, Human-AI Interaction, Mathematical Analysis.
- Tutor for first-year students at Innopolis University (Sep 2023 – Jan 2024), helping newcomers acclimate and organizing community events.
- Always exploring ways to make LLM tooling more accessible and efficient.
- Portfolio: 1kkiren.ru
- Email: [email protected]
- Profiles: GitHub