Key Facts

Remote From:

Freelance

German

Hard Skills

Text Extraction Web Crawling Puppeteer (Software) Automation Anywhere (RPA Software) Azure OpenAI Web Crawling Web Crawling Software Architecture Playwright (Software Testing) Application Programming Interface (API) +10 more

Other Skills

•
Teamwork
•
Communication

Roles & Responsibilities

Experience with web scraping and crawling tools (BeautifulSoup, Scrapy, Playwright, Puppeteer, or similar frameworks)
Strong knowledge of content extraction and text analysis
Hands-on experience integrating AI/LLM APIs (e.g., OpenAI, Anthropic, or open-source models)
Ability to design and build clean, maintainable software products, not just quick prototypes

Requirements:

Develop a web crawling and scraping system to collect relevant data from a list of websites
Extract and process meaningful content from crawled pages
Integrate AI/LLM capabilities to analyze website content and evaluate whether the company fits a target industry vertical
Design a scoring or ranking mechanism that qualifies and prioritizes leads

MENA Alliances

About MENA Alliances

MENA Alliances is a woman-owned business dedicated to connecting global companies with highly-skilled, vetted talent from the MENA (the Middle East and North Africa) region. We source top-notch candidates for you by tapping into our rich network of the MENA region’s best tech pros. Our vetted professionals are experienced and ready to go, and training is rarely required. Ex: Software engineers, programmers, designers, translators, and more at the click of a button. Spending your childhood and youth in a refugee camp and conflict zone could lead you to believe that there is no opportunity available to you in the world. No opportunity means no hope. We wanted to change that for ambitious, talented people who have the skills but are under-employed. Scale your business by building remote teams from MENA’s ambitious top professionals. MENA Alliances Mission: Our mission is to help women and young professionals in the MENA region access the self-determination that comes with in-demand skills and career opportunities. Everyone deserves to reach their full potential, find their passion, and achieve success - no matter where in the world they live. We believe in a world where location is no longer a barrier for diligent, talented people to reach for the success they envision for their future. Our clients range from large enterprises with mega data projects to startups wanting to hire experienced developers. Our core services include: Qualified Professionals On-Demand Translation & Localization Data Labelling & Annotation Our Impact on Numbers: More than 700 jobs offered have been implemented by more than 700 professionals (primarily women and youth). More than 3000 youth and graduates have been trained on skills and tools that enable them to work online and compete in the global market. Her company has reached Global markets such as the US, UK, Swaziland, Germany, Netherlands, and the Gulf region.

Founded: 2018

Company size: 11 - 50

LinkedIn See all jobs →

Job description

This is a remote position.

MENA Alliances is hiring a Web Crawling & AI Lead Qualification Engineer to develop a smart tool that identifies and evaluates potential business leads.

In this role, you will build a web crawling and AI-powered lead qualification application that takes a list of company websites, extracts relevant content, and uses AI to determine whether those companies are strong marketing targets for specific industry sectors (such as utilities or telecom).

The final deliverable should be a clean, maintainable, and handover-ready product that the end client can easily operate and expand.

Key Responsibilities

Develop a web crawling and scraping system to collect relevant data from a list of websites.
Extract and process meaningful content from crawled pages.
Integrate AI/LLM capabilities to analyze website content and evaluate whether the company fits a target industry vertical.
Design a scoring or ranking mechanism that qualifies and prioritizes leads.
Produce a structured output containing qualified leads with clear reasoning or scoring.
Deliver a standalone, well-structured application ready for handover to the client.

Requirements

Technical Requirements

Experience with web scraping and crawling tools such as BeautifulSoup, Scrapy, Playwright, Puppeteer, or similar frameworks.
Strong knowledge of content extraction and text analysis.
Hands-on experience integrating AI / LLM APIs (e.g., OpenAI, Anthropic, or open-source models).
Ability to design and build clean, maintainable software products, not just quick prototypes.
Familiarity with modern development stacks and best practices.

Nice to Have

Experience in lead generation, marketing technology, or sales intelligence tools.
Knowledge of prompt engineering, particularly for multilingual or non-English content.
Experience building end-to-end AI-powered tools or automation solutions.
German language skills are a plus but not required (language support will be provided by the client).