Skip to content
View Azat-Shakirov's full-sized avatar

Highlights

  • Pro

Block or report Azat-Shakirov

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 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
azat-shakirov/README.md

Azat Shakirov

CS Student · AI/LLM Developer · Security Enthusiast
Knox College · Galesburg, IL

Portfolio · LinkedIn · Email


$ whoami

I build AI systems and security tooling while finishing my CS degree. The focus is production — things that actually run, fail, and get fixed. Right now that means RAG pipelines, LLM orchestration, and SOC automation. Four languages (English · Russian · Kyrgyz · Chinese), in search of immortality.


$ cat stack.md

AI / LLM Python Claude API LangChain ChromaDB

Backend / Infra FastAPI Flask Docker n8n Railway

Security / SOC Splunk ELK Linux Bash

Frontend / Web JavaScript Vercel Git


$ ls ./featured

Production RAG pipeline on Railway. ChromaDB + LangChain + Claude API with reCAPTCHA v3/v2, a custom sliding-window rate limiter (the SlowAPI integration was silently doing nothing), prompt-injection sanitization, and a 50k daily token budget. Cut Docker image from 5.8 GB to under 4 GB. Fixed 15s response times traced to an unpinned dependency reloading the embedding model on every request. LangChain · ChromaDB · FastAPI · Claude API · Railway

Three chained Claude API calls with structured JSON validation and automatic fallback handling. JD input to tailored .docx and Google Drive upload in under 60 seconds. Zero manual steps per application. Flask · n8n · Claude API · Google OAuth2 · python-docx

Log ingestion, normalization, and anomaly-detection pipeline over Splunk and ELK. n8n SOAR workflows with severity routing cut manual alert-handling by 70% across 1,000+ log entries per run. Splunk · ELK Stack · n8n · Flask · Python


$ ./contact.sh

Open to AI intern / SWE / SRE / DevOps roles · summer 2026 and beyond.

📫 azatshakirov789@gmail.com 🌐 portfolio-three-rho-w5f73tqssv.vercel.app 💼 linkedin.com/in/azatshakirov

Pinned Loading

  1. job-automation-pipeline job-automation-pipeline Public

    Python

  2. portfolio-chatbot portfolio-chatbot Public

    Python

  3. soc-dashboard soc-dashboard Public

    HTML