Skip to content
View MansurPro's full-sized avatar
😎
Working from Lab
😎
Working from Lab
19 followers · 42 following

Achievements

Achievement: Pull Sharkx4Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull Sharkx4Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault Contributor

Highlights

Block or report MansurPro

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
MansurPro/README.md

Mansurbek Satarov — Trustworthy AI Researcher, ML Systems Engineer, Full-Stack Developer. The stack I work across: interfaces, services and APIs, agents and RAG, models and training, systems and infrastructure.

studying how model behavior forms during training

Website Projects Research Contact

What I work on

I split my time between research that asks why models behave the way they do and engineering that puts those models in front of real users. Both halves feed each other.

Research Engineering
  • Trustworthy ML & alignment — making model behavior predictable, auditable, and safe to depend on
  • Learning dynamics & influence analysis — per-update gradient tracing to attribute behavior to training data
  • RLHF & preference optimization — how preference data and policy optimization shape behavior
  • LLM security — jailbreaks, data poisoning, and governing third-party agent extensions
  • Agentic AI & RAG — tool-using agents, orchestration graphs, grounded retrieval with honest citations
  • Computer vision & multimodal — detection and pose pipelines (YOLO, ViT-Pose); text ↔ image ↔ video
  • Scalable deployment — GPU serving, containerized inference, reproducible training infra
  • Backend & APIs — FastAPI, Django, Flask, Node; REST and GraphQL over Postgres, MongoDB, Redis
  • Frontend — React, Next.js, Vue, TypeScript, Tailwind, Three.js — accessible and fast by default
  • Cloud & DevOps — Docker, Kubernetes, GCP/AWS/Azure, GitHub Actions CI/CD, Nginx
  • Systems & OS — Linux internals, C/C++/Rust, shell and process tooling, containers from the ground up
  • System design — service boundaries, caching layers, data modeling, and the failure modes of each
  • Data engineering — ingestion, cleaning, feature pipelines, warehouse-backed analytics
  • Automation — CI pipelines, scheduled jobs, and bots that remove manual steps

Ph.D. Research Assistant at the University of Cincinnati · part-time Research Assistant at the P&G Digital Accelerator

Research interests

Active — where my current work lives.

Trustworthy ML Alignment RLHF Learning dynamics Influence analysis LLM security Agentic AI Retrieval-augmented generation Computer vision Multimodal learning Scalable model deployment

In preparation — adjacent ground I read into and expect to work in next.

Mechanistic interpretability Model evaluation and benchmarking Uncertainty quantification and calibration Adversarial robustness Parameter-efficient fine-tuning Data-centric AI Synthetic data Privacy-preserving ML Reasoning and planning Efficient inference Human oversight Reproducible ML infrastructure

Each of these has a page with context on mansurpro.netlify.app/research.

Selected work

AI, LLMs & agents
Project What it does
Multi-Agent Deep Research LangGraph supervisor/worker workflow that plans research, gathers live evidence, extracts structured findings with Pydantic schemas, and writes sourced reports
RAG Assistant Modular retrieval-augmented generation pipeline — ingestion, chunking, embeddings, ChromaDB semantic search, conversational interface
Prompt2Clip Text-to-video generation on scalable cloud GPU infrastructure using the Mochi model
Data, cloud & full-stack
Project What it does
Retail Intelligence Platform End-to-end Azure analytics — customer lifetime value, churn risk, basket associations — served through FastAPI + React with a SQL-backed dashboard cache
DocuParse PDF/EPUB/MOBI → clean structured Markdown, with AI layout detection, LaTeX equation handling, and multilingual support
College Inquiry Chatbot Cloud-native conversational system on GCP that answers prospective-student questions
Systems & fundamentals
Project What it does
DigitRecognizer MNIST classifier written from scratch in NumPy — forward pass, backprop, gradient descent, zero frameworks
DinoMind Evolution NEAT neuroevolution learns a timing-critical game with no gradients and no labeled data

More at mansurpro.netlify.app.

Tech I actually use

Languages & core  14
Python
Python		 JavaScript
JavaScript		 TypeScript
TypeScript		 Java
Java		 Rust
Rust		 C
C		 C++
C++
PHP
PHP		 R
R		 Bash
Bash		 PowerShell
PowerShell		 Regex
Regex		 LaTeX
LaTeX		 WebAssembly
WebAssembly
AI / ML / data  5
PyTorch
PyTorch		 TensorFlow
TensorFlow		 scikit-learn
scikit-learn		 OpenCV
OpenCV		 Anaconda
Anaconda
Backend & APIs  7
Django
Django		 Flask
Flask		 FastAPI
FastAPI		 Node.js
Node.js		 Rails
Rails		 GraphQL
GraphQL		 Nginx
Nginx
Frontend  14
React
React		 Next.js
Next.js		 Vue
Vue		 Nuxt
Nuxt		 Redux
Redux		 jQuery
jQuery		 Tailwind
Tailwind
Bootstrap
Bootstrap		 Material UI
Material UI		 Sass
Sass		 Three.js
Three.js		 SVG
SVG		 Vite
Vite		 Webpack
Webpack
Databases  7
PostgreSQL
PostgreSQL		 MySQL
MySQL		 MongoDB
MongoDB		 Redis
Redis		 SQLite
SQLite		 Supabase
Supabase		 Firebase
Firebase
Cloud, DevOps & OS  18
Docker
Docker		 Kubernetes
Kubernetes		 AWS
AWS		 GCP
GCP		 Azure
Azure		 Cloudflare
Cloudflare		 Heroku
Heroku
Netlify
Netlify		 Vercel
Vercel		 Linux
Linux		 Ubuntu
Ubuntu		 Windows
Windows		 Git
Git		 GitHub
GitHub
Actions
Actions		 npm
npm		 pnpm
pnpm		 Yarn
Yarn
Tools & platforms  14
Figma
Figma		 Photoshop
Photoshop		 Notion
Notion		 Postman
Postman		 VS Code
VS Code		 WebStorm
WebStorm		 Vim
Vim
Replit
Replit		 CodePen
CodePen		 Stack Overflow
Stack Overflow		 WordPress
WordPress		 Gmail
Gmail		 LinkedIn
LinkedIn		 Bots
Bots

Contribution graph

Isometric 3D contribution graph for the last year

Rendered from the GitHub contributions API by assets/contrib.gen.py and refreshed daily by a scheduled Action — column height tracks that day's contribution count.

Stats

GitHub stats Contribution streak

Most used languages Most committed languages

Open to research collaborations and industry opportunities.
sataromk@mail.uc.edu · LinkedIn · mansurpro.netlify.app

Hits

Pinned Loading

  1. Shareme Shareme Public

    Social media web app

    JavaScript 2

  2. Car-show Car-show Public

    Car show - rental cars

    TypeScript 1

  3. Prompt2Clip Prompt2Clip Public

    Prompt2Clip is a cloud-based application for generating high-quality videos from textual prompts using the Mochi video generation model. This project demonstrates the integration of advanced AI mod…

    Jupyter Notebook 2 1

  4. DinoMindEvolution DinoMindEvolution Public

    This project uses neural evolution to train a neural network to play the Google Chrome Dinosaur Game autonomously.

    Python

  5. machine-learning-projects machine-learning-projects Public

    Machine learning projects from Grokking Machine Learning by Luis Serrano

    Jupyter Notebook

  6. RAG-assistant RAG-assistant Public

    RAG-assistant is a type of AI assistant that uses Retrieval-Augmented Generation to provide more accurate and context-rich answers by combining a large language model (LLM) with an external knowled…

    Python