Hiring Agent
A local AI resume scoring tool ranks PDF applications with editable role rubrics and evidence for each score, using Ollama or cloud models.
Hiring Agent helps hiring teams rank resume PDFs to decide which applications to review first. HackerRank built it for intern applications, with human reviewers making the hiring decisions.
- Resume scoring: Extracts work history, education, skills and projects, then returns category scores with supporting evidence, bonus points and deductions.
- Role-specific rubrics: Teams can edit scoring categories, weights and prompts for each role. The supplied software engineering intern rubric covers open source contributions, personal projects, production experience, technical skills and AI fluency.
- GitHub context: When a resume includes a GitHub profile, the tool fetches profile and repository information to assess project work and contributions.
- Evaluation exports: Reports include score explanations, while an optional development mode saves CSV results and caches intermediate data.
The Python tool is open source under the MIT license. Ollama runs model inference locally, with Gemma 4 among the supported models. Google Gemini and OpenAI are cloud alternatives that require API keys and send model requests to their services. GitHub enrichment needs network access even with local inference.
Scores can vary between evaluations of the same resume, and invisible text in PDFs can inflate results. The GitHub-focused rubric can disadvantage candidates whose work is in private repositories. Evidence interpretation depends on the model.
