AI-Assisted Institutional Accreditation Analytics: Automating NAAC Metric Preparation

About Internship

Assistant Professor from CHARUSAT university , is accepting candidates interested in the field of Computer Science, in the research area of Artificial intelligence and Machine learning.

Indian higher-education institutions spend enormous IQAC staff-time each accreditation cycle manually locating, cross-checking, and formatting the evidence required for NAAC's QnM and QlM metrics — work that is repetitive, error-prone, and poorly suited to manual effort at scale. This internship is a pilot to test whether AI can meaningfully reduce that burden, starting with Criterion 2 (Teaching-Learning & Evaluation) as the proof-of-concept criterion. Interns will work on building a working pipeline/tool that ingests institutional records (attendance data, evaluation records, faculty documentation, etc.) and assists in extracting, structuring, and validating the specific data points each QnM sub-metric requires — alongside a structured process document capturing how the workflow generalizes to other criteria. The goal is a genuinely useful applied-AI system, not a toy demo: output quality is judged against what an actual IQAC office could use during a real accreditation cycle. There's also a research-writing dimension — this is a relatively unexplored niche in applied-AI literature (most existing work discusses accreditation automation conceptually rather than as working systems), so a well-documented pilot has publication potential. Skills Required from Candidates Coding / technical skills Python, with comfort in document/text processing (parsing PDFs, spreadsheets, structured and semi-structured records) Experience with LLM APIs and prompt engineering for structured data extraction (function calling / structured outputs) Basic familiarity with spreadsheet-based data validation and template design (Excel/Google Sheets)