All work
Development · Python
AI Recruitment Engine — FastAPI Microservice
The Python AI brain behind my recruitment platforms — a ~2,300-line FastAPI service doing CV shortlisting (embeddings + LLM + keyword), AI voice interviews, Whisper transcription and job-description generation.
The FastAPI microservice that powers the AI in my Career/recruitment products (the pyscript/ service behind the Laravel app): it scores and ranks CVs, runs automated voice interviews end-to-end, transcribes audio with Whisper and generates job descriptions — degrading gracefully to deterministic stubs when no API key is set.
PythonFastAPIOpenAIWhisperscikit-learnPyMuPDFRedis
What it does
- Hybrid CV scoring — deterministic baseline + OpenAI embeddings (text-embedding-3-large, cosine similarity) + LLM evaluation + keyword match, combined into one rank.
- AI voice interviews — session endpoints (start → question → response → complete) with Whisper transcription and per-answer clarity/relevance scoring.
- PDF résumé parsing (PyMuPDF), scikit-learn / NumPy similarity math and Redis-backed session state.
- Auto job-description generation across industry categories with role auto-detection.
- Graceful degradation — deterministic stubs when OPENAI_API_KEY is unset, so the whole app keeps working with AI off.
- Clean async FastAPI + Uvicorn service with a /health check, called from Laravel over HTTP.
Next step
Get started today.
A free consultation, no commitment. Tell us what you need and you get a written plan and quote within one business day, from the engineer who will build it.
- Free
- first consultation
- 1 day
- to a written quote
- Weekly
- working demos
- Yours
- source code at handover