Data Mining & OSINT Automation Specialist (m/f/d)

About Project IRIS Project

IRIS is an applied research and technology initiative dedicated to automated spatial data analysis, infrastructure mapping, and open-source data modeling. Because not all valuable data exists as clean spatial polygons, we build systems that extract hidden knowledge from texts, complex web registries, and unstructured documents. In this role, you will build the autonomous agents that feed our intelligence engine.

Your Focus & Responsibilities

• Web Automation: Develop scalable web scrapers and autonomous agents to extract data from unstructured sources (public registers, official announcements, corporate portals).
• Data Parsing: Parse unstructured web and document data (JSON, XML, HTML, PDF) into clean, relational database structures.
• Entity Extraction: Apply OCR, regex, and NLP techniques to extract structured entities (addresses, capacities, corporate connections) from dense documents.
• Pipeline Monitoring: Automate monitoring scripts to continuously feed fresh data into our central PostGIS Data Lake.

What We Are Looking For

• Technical Background: Degree in Computer Science, Software Engineering, Data Analytics, or equivalent practical industry experience.
• Core Technical Skills: Proven experience in Web Scraping (Python, Playwright, Scrapy, Selenium, BeautifulSoup) and handling uncooperative web architectures.
• Mindset: Analytical mindset with a drive for data cleaning, structural modeling, and robust automation.
• Eligibility: Open to local applicants and international candidates (Chancenkarte / Opportunity Card supported).
• Languages: Professional working proficiency in English (required); German language skills are a plus.