+
Skip to content
View spqr-86's full-sized avatar

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Block or report spqr-86

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
spqr-86/README.md

Hi, i'm Petr 👋

AI Engineer | LLM Developer | RAG Specialist

🚀 About Me

🔭 Currently working on AI Safety Incident Analyzer - AI-powered system for industrial safety analysis

🌱 Deep diving into Advanced RAG techniques and Multi-Agent Systems

👯 Looking to collaborate on LLM/RAG projects with real-world impact

💬 Ask me about LangChain, RAG systems, Prompt Engineering, or Industrial Safety

📫 Reach me at: petr.baldaev.ds@gmail.com or @PetrBaldaev

⚡ Fun fact: I combine 15 years of industrial safety expertise with modern AI to solve real problems

🛠️ Tech Stack

AI/ML & NLP

Python OpenAI LangChain Hugging Face PyTorch scikit-learn

Backend & APIs

FastAPI Django DjangoREST Flask

Databases & Vector Stores

PostgreSQL MySQL ChromaDB Pinecone Qdrant

DevOps & Tools

Docker Git Nginx Railway

📫 Let's Connect!

💼 Open for AI/LLM Engineer positions

🌍 Location: Moscow, Russia (open to relocation)

🚀 Always interested in challenging AI projects

🔥 Featured Projects

Pinned Loading

  1. safety-incident-analyzer safety-incident-analyzer Public

    An AI-powered RAG system to analyze and query 500+ Russian industrial safety documents (SNiP, GOST), reducing expert analysis time from 3 hours to 15 minutes.

    Python

  2. titanic-booking-ai titanic-booking-ai Public

    A conversational AI agent simulating a 1912 Titanic booking clerk, maintaining historical accuracy (94% factual precision) and character consistency through advanced prompt engineering.

    Python

  3. financial-telegram-bot financial-telegram-bot Public

    An NLP-powered Telegram bot for seamless expense tracking via natural language. Processed over 1,200 real-user transactions with 91% parsing accuracy and 86% categorization accuracy.

    Python

  4. gitlab-onboarding-rag gitlab-onboarding-rag Public

    A multilingual (RU/EN) RAG system built on 847 pages of GitLab documentation to provide instant answers for new employees, achieving 89% response accuracy and sub-3-second latency.

    HTML

  5. Data_Science_Projects Data_Science_Projects Public

    Data_Science_Projects

    Jupyter Notebook

  6. BBBS BBBS Public

    Forked from hlystovea/BBBS

    🌐 A site to help mentors work with children.

    Python

点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载