{"slug": "hirelens-ai-building-an-open-weight-ai-recruitment-platform-for-small-businesses", "title": "HireLens AI: Building an Open-Weight AI Recruitment Platform for Small Businesses", "summary": "A developer built HireLens AI, an open-source, open-weight recruitment and applicant tracking platform aimed at small businesses and recruitment agencies. The system extracts structured candidate data from PDF and DOCX resumes using open-weight model inference (including local Ollama deployments), but keeps candidate scoring in deterministic Python logic so the LLM only generates grounded explanations rather than hiring or rejection decisions. The full-stack app runs on FastAPI, PostgreSQL and SQLAlchemy with tenant-aware data access, deployed on Vercel, Render and Neon with a one-click synthetic-data demo.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle](https://dev.to/challenges/hacktoberfest-week2-2026-10-12)*\n\nI built **HireLens AI**, an AI-powered recruitment and applicant tracking platform designed for small businesses, startups, and recruitment agencies.\n\nHiring is expensive and time-consuming, especially for small teams that cannot afford dedicated recruitment departments or expensive enterprise hiring software.\n\nRecruiters often spend hours:\n\nHireLens AI brings these workflows into one recruitment workspace.\n\nIts key capabilities include:\n\nThe goal is simple: give smaller recruitment teams access to useful hiring intelligence without the complexity and cost of enterprise recruitment platforms.\n\n**Live Application:** [https://hire-lens-black.vercel.app](https://hire-lens-black.vercel.app)\n\nThe application includes a one-click demo experience.\n\nVisitors can explore the platform as a fictional demo recruiter, Alex Morgan, without creating an account or entering credentials.\n\nThe demo includes synthetic candidates, sample job openings, resume workflows, and explainable matching results.\n\nThe platform also protects its demo workspace against destructive operations and isolates demo data from other tenants.\n\n*Note: The free backend hosting may take a little time to wake up after inactivity.*\n\n**GitHub Repository:** [https://github.com/kusalar/HireLens](https://github.com/kusalar/HireLens)\n\nThe project uses a full-stack architecture:\n\nI wanted HireLens AI to be more than another chatbot that generates recruitment recommendations.\n\nI designed it around a combination of open-weight AI, conventional backend engineering, and deterministic decision logic.\n\n**1. Resume Intelligence**\n\nThe platform extracts information from PDF and DOCX resumes and converts it into structured candidate information.\n\nThe architecture supports open-weight model inference, including local development with Ollama and hosted open-weight inference.\n\n**2. Deterministic Candidate Matching**\n\nOne of the most important architectural decisions was separating candidate scoring from language model generation.\n\nThe matching score is calculated using deterministic Python logic.\n\nThe LLM does not decide who should be hired, does not autonomously reject candidates, and does not control the final matching score.\n\nInstead, AI assists with grounded explanations that help recruiters understand the matching results.\n\n**3. Recruitment Workspace**\n\nI built the recruitment workflow around jobs, candidates, applications, resume processing, matching, comparison, and pipeline management.\n\nThe backend uses FastAPI, PostgreSQL, SQLAlchemy, and tenant-aware data access to support multiple recruitment organizations.\n\n**4. Production Deployment**\n\nI deployed the frontend on Vercel, the backend on Render, and the PostgreSQL database on Neon.\n\nI also implemented a publicly accessible one-click demo mode so evaluators can explore the actual application.\n\nThe current deployment uses free-tier infrastructure, making it possible to demonstrate the product without maintaining expensive hosting services.\n\nFor HireLens AI, open innovation is not just about using a different AI model. It is about having control over the technology that powers the product.\n\nRecruitment platforms process sensitive information. Resumes can contain contact details, employment histories, education records, and other personal information.\n\nBuilding around open-weight models gives us more control over where inference happens and how models are deployed.\n\nThere are several important advantages:\n\n**1. Model Independence**\n\nI do not want the entire product to depend on a single proprietary AI provider.\n\nOpen-weight models give us the flexibility to experiment with different models, change inference providers, and adapt the system as the product grows.\n\n**2. Cost Control**\n\nA recruitment SaaS for small businesses needs sustainable economics.\n\nDepending entirely on expensive proprietary inference APIs could make the product difficult to operate at scale.\n\nOpen-weight inference gives us the option to explore local and self-hosted deployments and better control inference costs.\n\n**3. Data Control**\n\nLocal inference can provide an additional privacy option for organizations that do not want resume content sent to external AI providers.\n\nIt also creates opportunities for future private deployments.\n\n**4. Transparent and Controlled Decisions**\n\nI deliberately kept candidate scoring deterministic rather than allowing an LLM to make hiring decisions.\n\nThis makes matching more reproducible and easier to test, while AI-generated explanations help recruiters understand the results.\n\nFor me, open innovation means being able to inspect, adapt, replace, and control important parts of the technology instead of building the entire business around someone else's API.\n\n**Built with the idea that powerful recruitment intelligence should be accessible to smaller teams, not just enterprises.**\n\nThanks for checking out HireLens AI!", "url": "https://wpnews.pro/news/hirelens-ai-building-an-open-weight-ai-recruitment-platform-for-small-businesses", "canonical_source": "https://dev.to/kusal_099098/hirelens-ai-building-an-open-weight-ai-recruitment-platform-for-small-businesses-1k3i", "published_at": "2026-10-18 11:10:36+00:00", "updated_at": "2026-10-18 11:15:23.932365+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-products", "ai-tools", "large-language-models", "ai-agents"], "entities": ["HireLens AI", "Ollama", "FastAPI", "PostgreSQL", "SQLAlchemy", "Vercel", "Render", "Neon"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/hirelens-ai-building-an-open-weight-ai-recruitment-platform-for-small-businesses", "markdown": "https://wpnews.pro/news/hirelens-ai-building-an-open-weight-ai-recruitment-platform-for-small-businesses.md", "text": "https://wpnews.pro/news/hirelens-ai-building-an-open-weight-ai-recruitment-platform-for-small-businesses.txt", "jsonld": "https://wpnews.pro/news/hirelens-ai-building-an-open-weight-ai-recruitment-platform-for-small-businesses.jsonld"}}