masood.sultan
Geoscientist & AI Engineer - Berlin

Decoding the Earth
through Code & AI

I am an AI engineer and geophysicist specializing in computational geoscience and autonomous data systems. I build platforms that ingest planetary-scale data - from real-time disaster APIs to satellite imagery - and transform it into actionable intelligence. My background ranges from 3D subsurface geomodelling to developing self-learning scrapers and deployment-ready climate monitoring architectures.

Masood Sultan
Open to research positions
scroll
01
TypeScript Node.js Express SSE

TerraMind Core

A real-time global disaster intelligence platform entirely powered by open government APIs. It dynamically aggregates and normalizes data from USGS Earthquakes, NASA EONET Wildfires, NOAA Weather Alerts, and NASA FIRMS Satellite Fire Detection into a single unified stream. Features a built-in GeoScience AI Assistant to help developers and scientists map disaster impacts using remote sensing.

4 Gov APIs Unified Multi-source normalizer pipeline for global coverage
Server-Sent Events (SSE) Real-time push engine without polling delays
Interactive Dashboard Live map markers, responsive UI, severity filters
View repository Live Dashboard
terramind-core
$ npm start
[server] TerraMind API Engine booting on port 4100
[pipeline] Normalizing mult-source hazard feeds...
[usgs] Extracted 8 seismic anomalies
[nasa-firms] Scanning VIIRS 375m fire detections
[sse] Broadcasting delta update to connected clients →
[status] 22 active events cached. Next sweep in 120s.
02
Python LLMs Self-Learning MIT License

ai-scraper

A web scraper that teaches itself. Point it at any website - it figures out the structure, extracts data using LLMs, and remembers what worked. Next time it hits the same domain, it's faster and more accurate. It builds domain-specific profiles, scores its own output quality, and auto-evolves its extraction prompts. Headless Chrome under the hood, with persistent memory that compounds over time.

Self-Evolving Prompts Gets smarter with every single scrape
Persistent Memory Domain profiling that compounds over time
Quality Scoring Self-evaluates extraction accuracy
View repository
ai-scraper
$ python scraper.py --url "https://arxiv.org/list/physics.geo-ph"
[engine] No domain profile found. Learning...
[chrome] Headless browser launched
[llm] Analyzing page structure...
[learn] Domain profile created: arxiv.org
[learn] Extraction accuracy: 94.7%
[done] 127 papers extracted → papers.json
03
Python Telegram Automation AGPL-3.0

openhouse-bot

Born out of frustration with Berlin's brutal housing market. This bot crawls 50+ real estate portals worldwide, applies your exact filters - price, rooms, location, commute time - and fires matching listings to your Telegram 24/7. It uses an LLM-powered universal crawler that adapts to any portal's layout. Now features a Live Demo on Hugging Face to try the real-time scraping pipeline directly from your browser.

50+ Portals Global coverage, not just one platform
Instant Telegram Alerts New listings hit your phone in seconds
Live HF Demo Real-time scraping execution in browser
View repository Try Live Demo
openhouse-bot
$ python bot.py --city berlin --max-rent 900
[bot] Monitoring 54 portals...
[scan] immobilienscout24.de - 12 new
[scan] wg-gesucht.de - 4 new
[match] 2BR Kreuzberg €780 - SENT
[match] 1BR Neukölln €650 - SENT
[scan] Next cycle in 120s...

I didn't start in tech.
I started underground.

My first career was interpreting what's beneath your feet - 3D seismic surveys, subsurface geological models, wellbore data. I earned a BSc in Geophysics from Bahria University (3.55/4.00 CGPA) and placed 3rd in the Imperial Barrel Awards, Asia Pacific - one of the most competitive geoscience competitions organized by the AAPG.

Then I moved to Berlin for an MSc in Global Change Geography at Humboldt University, where the work shifted from subsurface to atmosphere - climate data, earth observation satellites, computational modelling. Somewhere along the way, I realized the tools I needed didn't exist. So I started building them.

Now I write Python instead of field reports. I build LLM-powered systems that crawl, extract, learn, and adapt. The geoscience training never left - it just evolved into a different kind of excavation.

Languages & Web

  • Python 3.x
  • TypeScript / Node.js
  • Express.js
  • HTML / CSS
  • R (RStudio)

AI & Automation

  • Agentic Systems (LLMs)
  • Open WebUI
  • Headless Web Scraping
  • Telegram Bots
  • Process Automation

Data & GeoScience

  • 3D Geomodelling (Petrel)
  • Spatial Analysis (QGIS)
  • Climate Data Analytics
  • Real-time APIS (FIRMS, USGS)
  • Pandas / NumPy

Infrastructure

  • Server-Sent Events (SSE)
  • REST API Architecture
  • Hugging Face Spaces
  • Docker / Appwrite
  • Git / PowerShell

Looking for a PhD position
in computational geoscience
or climate AI.

Also open to research collaborations, interesting side projects, or anything where geoscience meets code. Based in Berlin.