ICP persona generation system
Budget: $1,500 – $3,000 CAD
Project Title
Senior Python Developer – AI + Web Scraping (LangChain / FastAPI / Qdrant / GPT-4)
Project Description
About Us
AI Automation Consulting Inc. ( product-led-growth.com
| LinkedIn
) helps B2B companies build automated, AI-driven growth systems.
We are developing a SaaS platform that automatically gathers market intelligence and generates ICP (ideal customer profile) personas using AI + web scraping.
What We Need
A Python developer experienced in data pipelines, web scraping, and AI integration to help us build this platform’s backend.
You will:
Implement scalable FastAPI services for data ingestion and persona generation
Build web scraping pipelines using Bright Data API and Playwright (with fallback handling)
Process and clean scraped content, generate embeddings (OpenAI text-embedding-3-small)
Store and query data using Qdrant (vector DB) for RAG search
Integrate LangChain + GPT-4 for multi-persona generation (BDM/TDM/User)
Generate PDF and JSON reports via ReportLab / WeasyPrint
Containerize and deploy on AWS Lightsail or DigitalOcean (Docker + Compose)
Required Skills
Python 3.9+ (FastAPI / Flask / SQLAlchemy / Pydantic)
Web Scraping: Playwright, Selenium, Bright Data API, anti-bot bypass
AI & NLP: LangChain, OpenAI API (GPT-4), RAG implementation
Databases: PostgreSQL, Qdrant (or Pinecone/Weaviate), Redis cache
Workflow Automation: n8n or Airflow (ETL style tasks)
DevOps: Docker / Docker Compose, AWS or DigitalOcean deployment
Bonus: Next.js / React for front-end integration
Senior Python Developer – AI + Web Scraping (LangChain / FastAPI / Qdrant / GPT-4)
Project Description
About Us
AI Automation Consulting Inc. ( product-led-growth.com
) helps B2B companies build automated, AI-driven growth systems.
We are developing a SaaS platform that automatically gathers market intelligence and generates ICP (ideal customer profile) personas using AI + web scraping.
What We Need
A Python developer experienced in data pipelines, web scraping, and AI integration to help us build this platform’s backend.
You will:
Implement scalable FastAPI services for data ingestion and persona generation
Build web scraping pipelines using Bright Data API and Playwright (with fallback handling)
Process and clean scraped content, generate embeddings (OpenAI text-embedding-3-small)
Store and query data using Qdrant (vector DB) for RAG search
Integrate LangChain + GPT-4 for multi-persona generation (BDM/TDM/User)
Generate PDF and JSON reports via ReportLab / WeasyPrint
Containerize and deploy on AWS Lightsail or DigitalOcean (Docker + Compose)
Required Skills
Python 3.9+ (FastAPI / Flask / SQLAlchemy / Pydantic)
Web Scraping: Playwright, Selenium, Bright Data API, anti-bot bypass
AI & NLP: LangChain, OpenAI API (GPT-4), RAG implementation
Databases: PostgreSQL, Qdrant (or Pinecone/Weaviate), Redis cache
Workflow Automation: n8n or Airflow (ETL style tasks)
DevOps: Docker / Docker Compose, AWS or DigitalOcean deployment
Bonus: Next.js / React for front-end integration
Related categories:
Python
Web Scraping
Django
Amazon Web Services
PostgreSQL
Artificial Intelligence
Selenium
FastAPI
GPT-4
LangChain