Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197747,
        author = {Asad Farooque Azam},
        title = {CareerPath AI: A Hybrid Database and Large Language Model Approach to Skill-Based Career Recommendation for Engineering Students},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {6374-6379},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197747},
        abstract = {Career indecision among final-year engineering students is a pervasive problem that generic counselling sessions fail to address adequately. This paper presents CareerPath AI, a full-stack web application that recommends technology career paths from two complementary sources: (1) a proportion-based skill-matching engine querying a curated Firebase Firestore career database, and (2) a large language model (LLM) fallback using OpenAI GPT-3.5-turbo for goal-oriented or low-coverage inputs. The system employs a cascade hybrid architecture in which the database layer is always queried first; the LLM layer is triggered only when results are insufficient or when the user supplies free-text career goals rather than discrete skills. Testing across fifteen structured scenarios demonstrated sub-400 ms median response times for database queries and sub-3 s for LLM-assisted queries, with correct results in all fifteen cases. The paper documents the design, scoring algorithm, prompt engineering strategy, merge-and-deduplication logic, and lessons learned, and situates the work within the broader recommender systems and educational technology literature.},
        keywords = {career recommendation system, hybrid recommender, large language model, skill matching, Firebase Firestore, OpenAI GPT, educational technology, engineering students},
        month = {April},
        }