SN

Open to Data Science, ML & Automation roles — Moscow & remote

Saleh Noman

Data Scientist · Data & Automation Engineer

Web Scraping / ETL · Machine Learning · AI-Assisted Development

I build end-to-end machine-learning, web-scraping and ETL systems — and ship production tools fast with AI coding assistants.

Email LinkedIn GitHub Moscow, Russia
Saleh Noman — headshot
SN
5.0/5.0
GPA · Red Diploma
100%
Fortune-500 ATS detection
8+
Shipped projects

Builds production tools fast with AI coding assistants (Claude / GPT SDKs)

About

Turning messy web data into models and products

I'm a Data Science M.Sc. graduate from NUST MISIS (Honors / Red Diploma, GPA 5.0/5.0). I design and build the full pipeline — from resilient web scraping and data cleaning to machine-learning models and the apps that put them to work.

My Master's thesis built a hybrid rule-based + ML engine that detected the Applicant Tracking System of every Fortune 500 company with 100% coverage. Day to day I lead multi-source job-data ingestion at a data company, and I previously built the official scraping-template library for a desktop web-automation platform.

I work fluidly with AI coding assistants (Claude, GPT SDKs) to design agentic tooling and prototype quickly — moving faster without losing rigor. Fluent in English, native Arabic, working Russian.

  • Based in Moscow, Russia
  • 6+ years across data, automation & IT
  • Ships end-to-end, from scraper to UI

Open to Data Science, ML Engineering, Data / Automation Engineering, Web Scraping, Full-stack and IT Support roles — Moscow and remote.

5.0 / 5.0

GPA — M.Sc. Data Science, Red Diploma (Honors)

100%

Fortune-500 ATS detection (500 / 500)

8+

Shipped projects — ML, scraping, full-stack, desktop

6+ yrs

Across data, automation and IT support

Services

What I can build for you

I help businesses turn the open web into clean data and working automations — from resilient scrapers and lead lists to LinkedIn/social workflows, n8n pipelines and ML. Below are the platforms I've built scrapers and automations for.

Web scraping at scale

Resilient scrapers for e-commerce, social and SaaS — pagination, anti-bot handling, and exports to Google Sheets, a CMS, or webhooks.

Lead generation

Targeted B2B lead lists with enriched, verified contact data — emails, phones and social profiles, deduplicated and ready to use.

LinkedIn & social automation

Profile and company data extraction plus outreach workflows across LinkedIn and other social platforms.

n8n & RTILA workflows

Low-code/no-code automations wired to your existing tools — triggers, enrichment, and hand-offs that run on a schedule.

Data, ETL & ML

Cleaning, normalization and deduplication, dashboards, and machine-learning models with clear, explainable results.

Custom tools & apps

Packaged desktop and web tools — installers, dashboards and internal apps that put the data to work.

Platforms I've built scrapers & automations for

  • AmazonE-commerce
  • AliExpressE-commerce
  • eBayE-commerce
  • EtsyE-commerce
  • WalmartE-commerce
  • LinkedInSocial · Leads
  • InstagramSocial
  • FacebookSocial
  • Twitter / XSocial
  • Google MapsLocal · Leads
  • YelpLocal
  • IndeedJobs
  • RTILA StudioAutomation platform
  • n8nAutomation

Platform names and colours are shown for reference only — all trademarks belong to their respective owners.

Skills

A full-stack data toolkit — from scraper to model to UI

Top strengths

  • Python & Data (pandas, scikit-learn)95%
  • Web Scraping (Playwright, Selenium)93%
  • AI-Assisted Development (Claude / GPT SDKs)92%
  • ETL & Data Engineering88%
  • Machine Learning (CatBoost / XGBoost)85%
  • Automation (RTILA, n8n)84%
  • Full-stack (Flask / FastAPI / React)82%
  • SQL & Databases80%

Toolbox

Programming

  • Python
  • JavaScript
  • Java
  • C#
  • SQL

Data & ML

  • pandas
  • NumPy
  • scikit-learn
  • XGBoost
  • CatBoost
  • LightGBM
  • SHAP
  • Feature engineering
  • Cross-validation
  • F1 / precision / recall

AI & LLMs

  • AI-assisted development (Claude & GPT SDKs)
  • Agentic tooling
  • Prompt engineering
  • RAG-style pipelines

Scraping & Automation

  • Playwright
  • Selenium
  • Scrapling
  • BeautifulSoup
  • RTILA Studio
  • Anti-bot / stealth
  • Pagination
  • n8n

Web & Full-stack

  • Flask
  • FastAPI
  • React
  • Node.js / Express
  • Supabase
  • REST APIs
  • Alpine.js

Data Engineering

  • ETL
  • Normalization
  • Deduplication
  • Validation gates
  • Freshness tracking
  • Directus API
  • Google Sheets API

Databases

  • PostgreSQL
  • MongoDB
  • Firebase
  • SQLite
  • Supabase

Tooling & IT

  • Git
  • pytest
  • GitHub Actions CI/CD
  • PyInstaller
  • Jupyter
  • System administration
  • Deployments
  • Documentation

Languages

  • Arabic · Native
  • English · Fluent · C1
  • Russian · Intermediate · B1
  • Japanese · Elementary · A1

Experience

Six years across data, automation and IT

  1. Data Aggregation & Automation Manager (ETL Lead)

    Sep 2025 – Present

    Data & Analytics Company RemoteCurrent

    • Own end-to-end scraping & ETL for multi-source job listings: discovery → extraction → cleaning → normalization → load to a headless CMS (Directus).
    • Built an AI-assisted, multi-source scraping platform (FastAPI + Playwright) with an agentic source builder (Claude / GPT SDKs) that generates validated scraper configs from any job-board URL; 200+ automated tests.
    • Implemented QA gates — dedup rules, timestamp normalization, schema validation and freshness tracking (first_seen / last_seen) — with scheduling, logging and alerting.
  2. Data Automation Specialist & Application Support

    Jan 2023 – 2026

    Web-Automation / RPA Product Company Remote

    • Built the official library of scraping templates and standalone bots for a desktop RPA / web-automation product, covering e-commerce, social and SaaS platforms (Amazon, AliExpress, Etsy, LinkedIn, Google Maps and more).
    • Engineered resilient extractions (CSS / XPath selectors, pagination, anti-bot techniques); wired outputs to Google Sheets, MySQL, a headless CMS and webhooks.
    • Authored troubleshooting guides, trained internal and external support teams, and directed weekly production releases with change management and impact analysis.
  3. IT Support Specialist

    Sep 2019 – 2023

    Yemeni Socialist Party Sana'a

    • Upgraded operating systems and software institution-wide, secured equipment and data, and reached a 100% troubleshooting success rate.
    • Improved work efficiency ~50% through system updates; trained employees, boosting productivity ~40%.
  4. Volunteer English Language Teacher

    2018 – 2020

    Community Programme Sana'a, Yemen

    • Taught high-school students English grammar and exam technique; 100% of students passed final exams, ~60% with excellent grades.

Projects

Selected work — shipped end-to-end

Machine learning, resilient web scraping, ETL, automation and full-stack apps — including commercial, licensed products. Click any card for the full case study.

More builds

BST / AVL Benchmarking Study

Python + C++ study benchmarking binary-search-tree vs. AVL-tree operations on random and sorted datasets, with plotted results and a matched C++ runner for large runs.

  • Python
  • C++
  • Matplotlib

Service-Provider Marketplace App

Android marketplace that matches service providers with clients by category, price, location, availability and ratings.

  • Android
  • Java
  • Firebase

Retail POS / Accounting System

Point-of-sale and accounting system tracking daily sales, inventory and customer accounts — reduced manual errors for a retail business.

  • C#
  • SQL
  • Desktop

Education & Certifications

Formal training in data science, IT and languages

Education

  • M.Sc., Data Science — Honors (Red Diploma), GPA 5.0/5.0

    2024 – 2026

    NUST MISIS — National University of Science and Technology, Moscow

  • B.Sc., Information Technology (92%)

    2017 – 2021

    University of Modern Sciences

  • Russian Language & Literature

    2023 – 2024

    Moscow Institute of Physics and Technology (MIPT)

  • Advanced English Diploma

    2016 – 2017

    Seeds Education

Honors

  • Red Diploma (Honors) — M.Sc. Data Science, NUST MISIS
  • Top-three student in class

Certifications

  • Google IT Support Professional CertificateCoursera · Sep 2022
  • IT Support FundamentalsCoursera · Feb 2022
  • The Bits and Bytes of Computer NetworkingCoursera · Mar 2022
  • Operating Systems and You: Becoming a Power UserCoursera · May 2022
  • System Administration and IT Infrastructure ServicesCoursera · Jul 2022
  • IT Security: Defense Against the Digital Dark ArtsCoursera · Sep 2022
  • Foundations of User Experience (UX) DesignCoursera · Oct 2022
  • Start the UX Design Process: Empathize, Define & IdeateCoursera · Nov 2022
  • Information Systems Auditing, Controls & AssuranceHKUST · Dec 2023
  • English Teacher Training ProgramI Learn Academy · 2017

Work with me

Start a project or book a consultation

Tell me a little about your project — scraping, lead generation, automation, or data/ML — and I'll reply with next steps and a quick plan. Open to Data Science, ML Engineering, Data / Automation Engineering, Web Scraping, Full-stack and IT Support roles — Moscow and remote.

Tell me about your project