Maze AI
AI-powered skills matching engine that reduces CV-to-interview shortlisting from days to seconds. Bayseian built the core scoring algorithm, CV parsing pipeline, and workflow orchestration layer.
The Challenge
Recruitment teams were spending days manually screening CVs, with poor matching quality leading to high volumes of irrelevant applications reaching hiring managers. Maze AI needed a production-grade intelligence layer, not a prototype.
Our Approach
Bayseian built a multi-dimensional attribute-based scoring algorithm, CV parsing pipeline with NLP extraction, a knowledge graph for skill taxonomy mapping, and n8n-based workflow orchestration. A Streamlit validation platform enables continuous model improvement.
Outcome
Shortlisting that previously took days now runs in seconds with significantly improved match quality. Maze AI was recognised as "Rising Star" at the London 2025 Startup Awards following the platform launch.
Highlights
- CV-to-job matching reduced from days to seconds
- Semantic skills extraction and matching
- Named "Rising Star" at London 2025 Startup Awards
- n8n-based workflow orchestration
Let's talk about your project
No pitch. A practical conversation about where AI fits in your operation.