AI Recruiting Assistant - A Hugging Face Space by 19arjun89

Spaces
1

:brain: Introducing AI Recruiting Assistant — A Responsible Hiring Assistant in Hugging Face Spaces

Hi everyone! :waving_hand:

I’m excited to share a new Hugging Face Space I’ve built: AI Recruiting Assistant — a Gradio-powered assistant designed to help automate candidate evaluation and cold email drafting while embedding responsible safeguards into the workflow.

:backhand_index_pointing_right: Check out the code: https://huggingface.co/spaces/19arjun89/AI_Recruiting_Agent/blob/main/app.py

:rocket: What It Does

This Space helps recruiters and talent teams do two main things:

  1. Assess Candidate Fit

    • Upload a batch of resumes and company culture documents

    • Paste in a job description

    • The assistant evaluates each candidate across skills match, culture fit, and produces an actionable hiring recommendation

  2. Generate Candidate-Specific Emails

    • Upload a single resume + job description

    • It produces a professional cold outreach email tailored to that candidate

:shield: Built-In Bias Mitigation & Verification

Because AI recruitment comes with real risks, I’ve built several safeguards into the design:

:small_blue_diamond: Input Anonymization

Resumes are sanitized of email, phone numbers, URLs, physical addresses, and other personal identifiers before any analysis or embedding. This helps reduce demographic leakage into similarity search and LLM reasoning.

:small_blue_diamond: Fact Verification

Every analysis (skills & culture) is verified against source inputs using a custom fact-checking prompt. Claims that aren’t supported are flagged and can trigger a self-correction routine.

:small_blue_diamond: Bias Audit Chain

For each candidate evaluation, the system runs a bias audit prompt that reviews:

  • Over-reliance on pedigree or subjective language

  • Penalization of nontraditional career paths

  • Unsupported reasoning outside the job description or culture docs

The audit produces structured feedback with bias indicators and a transparency note for recruiters to review.

These checks aren’t meant to replace human judgment, but to make AI support more transparent and fair.

:brick: Technical Highlights

  • Chroma vector stores to index resumes and culture documents for similarity search

  • Gradio UI for easy upload and interaction

  • LangChain + ChatGroq for orchestrating LLM analysis and auditing

  • Modular design to enable extensions (e.g., more fairness checks, analytics)

:megaphone: Feedback & Ideas Welcome

I’d love feedback from the community — especially on:

  • Other bias mitigation ideas that could be incorporated

  • Ways to improve candidate evaluation transparency

  • Performance & UX improvements on the Space

  • Choosing the right model for performing these types of people evaluations.

Thanks in advance for checking it out!

Happy building! :raising_hands: — Arjun