Job Description:
We are looking for an experienced developer or AI automation specialist to help us build a scalable solution for enriching and verifying data of architecture firms worldwide.
We already have a large dataset (stored in Google Sheets) and partial infrastructure set up, including:
Google Sheets (data source)
JavaScript-based scripts
Google Cloud API
Programmable Search Engine (Google CSE)
However, our current implementation has not yet achieved reliable results. We are seeking someone who can either help us fix and complete the existing system or propose a more effective AI-driven approach.
Scope of Work:
Your task will be to design and/or implement an automated workflow that can:
Find and fill in missing official websites for architecture firms
Verify and correct existing website URLs
Identify and fill in company location (country/city)
Count the number of architectural projects listed on the official website
Technical Requirements:
Strong experience with web scraping and automation
Experience with Google Sheets API / Apps Script
Familiarity with Google Cloud services
Experience using search APIs (e.g., Google Programmable Search Engine or alternatives)
Knowledge of AI tools (LLMs, agents, or scraping + parsing pipelines)
Ability to handle large-scale datasets efficiently
Nice to Have:
Experience with tools like Puppeteer, Playwright, or Selenium
Experience with AI-based extraction (e.g., using GPT or similar models for parsing websites)
Prior experience working with business directory or enrichment data
Ability to suggest improved architecture (e.g., hybrid scraping + AI validation pipeline)
Deliverables:
A working automated system (or improved version of our current one)
Clean and structured output written back into Google Sheets
Documentation of the workflow and setup
What We’re Looking For:
Someone who can not only implement but also propose better solutions
Strong problem-solving skills
Clear communication and ability to iterate quickly
To Apply:
Please include:
A brief explanation of how you would approach this problem
Relevant past projects (especially involving scraping, AI, or data pipelines)
Your suggested tech stack (if different from ours)
We are open to both short-term consulting and longer-term collaboration depending on results.
Looking forward to working with you!