Project Lead, TUM Stakeholder Collaboration
Education / AI Tooling · 2025
AI-Powered Academic Recognition & Planning Assistant
Led a team of 6 to build an AI assistant that automates academic credential recognition and study planning, helping international students navigate complex equivalency processes.
Context
Starting point and environment
International students face significant bureaucratic challenges when transferring academic credentials between institutions and countries. Manual evaluation is time-consuming, error-prone, and inconsistent, a problem I set out to address by assembling and leading a team of 6.
Challenge
Core constraint to solve
Lead a team to create a system that intelligently parses academic documents, maps curricula across different educational frameworks, and generates personalized study plans, while handling the enormous variety of international academic formats and validating the approach with TUM's admissions stakeholders.
Solution
Design and implementation approach
As Project Lead, directed a team of 6 through architecture, implementation, and validation. Conducted stakeholder interviews with TUM's Lead of Admissions & Program Administration to scope requirements and validate the solution. Developed an AI-powered pipeline that combines document parsing with intelligent curriculum mapping: the system analyzes transcripts, course descriptions, and institutional requirements to generate recognition recommendations and optimized study plans.
Outcome
Measurable impact and delivery result
Delivered, with the team, a functional tool validated by TUM's admissions stakeholders that dramatically reduces the time needed for academic credential evaluation. Demonstrates practical AI application in education administration, a domain where intelligent automation has massive untapped potential.
Key Takeaway
“This worked because it solved one painful problem clearly: student bureaucracy. Domain focus beat feature breadth.”

Working on something similar? I take on select consulting and freelance work in agentic AI, RAG systems, and LLM reliability.