Flagship case study
Recruitimate
An AI-native hiring platform that screens resumes, runs structured interviews, and scores candidates on what they actually say.
~50%
less manual shortlisting effort in internal trials
- The problem
- Hiring teams drown in resumes, and the AI interview tools that promise to help by scoring faces and tone are scientifically weak and now banned in EU hiring.
- What I built
- Next.js and TypeScript frontend; FastAPI backend on multi-tenant PostgreSQL; real-time interviews over LiveKit (WebRTC) with AssemblyAI streaming transcription; LLM scoring through the Claude and Gemini APIs using tool use and structured rubrics; retrieve-then-rerank resume screening on pgvector.
- The design principle
- Candidate scoring is grounded strictly in interview transcripts, with no facial or vocal affect inference, aligned with the EU AI Act.
~50%
less manual shortlisting effort in internal trials
Next.jsTypeScriptFastAPIPostgreSQLpgvectorLiveKitAssemblyAIClaude APIGemini API
