CareerLens is an AI-powered platform for semantic resume analysis and career growth intelligence. The system addresses limitations of traditional Applicant Tracking Systems (ATS) by combining transformer-based semantic embeddings, explainable scoring mechanisms, and seniority-aware calibration. The platform integrates resume parsing, semantic similarity computation, skill-gap analysis, and explainable AI techniques to provide transparent and actionable recommendations for candidates. CareerLens employs Sentence-BERT and BGE embeddings for dense semantic matching while incorporating domain-specific weighting strategies to account for experience level and career progression. The proposed architecture is designed to be CPU-efficient, fully open-source, and deployable in resource-constrained environments. In addition to resume-job matching, the system provides personalized skill recommendations, career insights, and interpretable score decomposition to improve user trust and decision-making. This work demonstrates the feasibility of fair, explainable, and semantically informed AI systems for recruitment and career development applications while emphasizing transparency, reproducibility, and ethical AI practices.
Doyel Mishra (Sat,) studied this question.