Skip to content
View KremlevLev's full-sized avatar
🏴‍☠️
sisyphean labor
🏴‍☠️
sisyphean labor
  • MIREA

Block or report KremlevLev

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
KremlevLev/README.md

𝔏𝔢𝔳 𝔎𝔯𝔢𝔪𝔩𝔢𝔳

"𝔅𝔲𝔦𝔩𝔡𝔦𝔫𝔤 𝔱𝔥𝔦𝔫𝔤𝔰 𝔣𝔯𝔬𝔪 𝔰𝔠𝔯𝔞𝔱𝔠𝔥 𝔲𝔫𝔱𝔦𝔩 𝔱𝔥𝔢𝔶 𝔴𝔬𝔯𝔨."

ML Engineer focused on LLM systems, AI agents and deep learning.

Interested in LLM architecture, SSMs, inference optimization and production ML.


⚔️ 𝔄𝔯𝔢𝔞𝔰 𝔬𝔣 𝔦𝔫𝔱𝔢𝔯𝔢𝔰𝔱

  • LLM architecture
  • Transformer / SSM hybrids
  • Mamba
  • inference optimization
  • AI agents
  • production ML

𝔖𝔱𝔞𝔠𝔨

Python · PyTorch · JAX · FastAPI · Docker · SQL · vLLM · Git · ...

𝔉𝔦𝔫𝔡 𝔪𝔢

GitHub Streak

Pinned Loading

  1. Rynne Rynne Public

    A deterministic Windows AI agent that doesn't hallucinate actions. Features native UI Automation (no blind clicks), file rollbacks, and strict HITL security.

    Python 8

  2. bpe-tokenizer-gpt bpe-tokenizer-gpt Public

    High-performance BPE tokenizer implemented from scratch with O(N log N) complexity. Architecturally identical to GPT-2/4.

    Python 1

  3. RAG-Pipeline-for-High-Load-Banking-Data RAG-Pipeline-for-High-Load-Banking-Data Public

    RAG pipeline for banking-domain question answering with hybrid retrieval, reranking, and local LLM generation.

    Python