Projects

Projects and case studies.

What the problems were, how I approached them, and what came out of it.

Featured Project — Deep Dive

Personal Research Project

Education / EdTech · 2026

Multi-Model AIEdTechKnowledge ExtractionFull-Stack

Quetzal: AI-Native Learning Platform with Knowledge Extraction

A personal project: an AI-powered learning platform built around document-grounded tutoring, adaptive assessments, and multi-model knowledge extraction.

Next.jsTypeScriptFastAPIPostgreSQLOpenAIGeminiAnthropicOCR
View Source

Context

Traditional learning platforms treat AI as a bolt-on feature. Students need systems that deeply understand their study material and adapt to their knowledge gaps.

Challenge

Build a multi-stage knowledge extraction engine that decomposes academic documents into atomic, scorable knowledge units — with accurate difficulty calibration, deduplication, and coverage guarantees across diverse academic domains.

Solution

Architected a constrained multi-model orchestration system (OpenAI, Gemini, Anthropic) with supervisor-based validation, anti-hallucination safeguards, and Bloom's Taxonomy-grounded difficulty calibration. Integrated OCR-based grading, progressive hinting, and Socratic interaction modes.

Outcome

A working platform that demonstrates multi-model AI orchestration at a level I'm genuinely happy with. Bloom's Taxonomy integration solved a calibration problem I hadn't expected to solve cleanly.

Key Takeaway

“Multi-model orchestration is the future of reliable AI — no single model is best at everything. Constrained generation with supervisor validation eliminated 90%+ of hallucination issues. Bloom's Taxonomy provided the missing structure for AI-generated educational content.”

Screenshots
Quetzal: AI-Native Learning Platform with Knowledge Extraction screenshot 1
1 / 10
Featured Project — Deep Dive

Bachelor's Thesis — TUM

AI Research / Trustworthy AI · 2025

Hallucination MitigationTrustworthy AIMulti-AgentNLP

Echo: Mitigating Hallucination Potential in User Prompts

My bachelor's thesis. A shift-left approach to LLM hallucination mitigation, tackling the problem at the prompt level rather than after generation.

ReactTypeScriptFastAPIPythonOpenAITailwind CSSRadix UI
View Source

Context

Current hallucination research overwhelmingly focuses on LLM-sided factors: training data quality, model architecture, decoding strategies. However, the user's prompt is a controllable input surface that significantly influences hallucination risk — yet this dimension remains vastly under-researched.

Challenge

Design a system that analyzes prompts before LLM generation to identify and mitigate hallucination-inducing patterns. Develop a novel taxonomy for user-sided hallucination risks and a quantitative metric for prompt risk assessment.

Solution

Built a multi-agent pipeline (Analyzer, Initiator, Conversation, Preparator) with a novel taxonomy distinguishing Prompt Risk (token-level ambiguity) from Meta Risk (structural issues). Introduced Prompt Risk Density (PRD) — a weighted metric for quantifying hallucination potential. Implemented iterative human-in-the-loop refinement with structured XML outputs and color-coded risk visualization.

Outcome

Demonstrated that shift-left prompt analysis reduces downstream hallucination risk. Contributed to the research discourse on trustworthy AI in high-stakes domains (law, healthcare, finance). Proved that better prompts can bridge the accessibility gap between expensive closed-source and smaller open-source models.

Key Takeaway

“Every LLM output has two actors — the model AND the user. Tackling hallucinations at the prompt level is more cost-effective and generalizable than post-generation detection. A structured taxonomy turned an abstract problem into a measurable, actionable framework.”

Echo: Mitigating Hallucination Potential in User Prompts screenshot 1
1 / 5

BCG Platinion — Energy Practice

Energy / Consulting · 2025–2026

Document IntelligenceNLPEnterprise AIEnergy

AI-Powered Contract Intelligence for Energy

Contributed to an AI-powered document intelligence solution for the energy sector, enabling automated extraction and analysis of complex contractual documents.

PythonAzure OpenAIOCRNLPFastAPI

Context

Energy companies manage large volumes of complex contracts and legal documents. Manual review processes are slow, inconsistent, and resource-intensive — creating bottlenecks across procurement, legal, and operations teams.

Challenge

Build a system that extracts structured information from dense legal documents and surfaces relevant insights for different stakeholder roles — each with different priorities and risk tolerances.

Solution

Contributed to an intelligent document processing pipeline combining OCR-based ingestion, targeted entity extraction, and a role-based query interface that surfaces relevant clauses and risk signals based on user function.

Outcome

Reduced document review time significantly. Enabled non-legal stakeholders to independently access decision-relevant information from complex agreements.

Key Takeaway

“Role-based AI interfaces dramatically increase adoption — generic dashboards get ignored. Designing for the end user's workflow, not the developer's convenience, is what separates useful AI from abandoned prototypes.”

Allianz SE — AI/ML Division

Insurance / Financial Services · 2024–2025

Agentic AIInsuranceWorkflow AutomationLLMs

GenAI Workflows for Insurance Operations

Developed GenAI applications to optimize information workflows and decision-making across customer communication, medical insights, and insurance evaluations.

PythonLangChainAzureCI/CDPrompt Engineering

Context

Insurance operations involve processing enormous volumes of customer communications, medical reports, and claim evaluations — each requiring domain expertise and careful judgment.

Challenge

Create AI systems that work reliably in a highly regulated environment, producing outputs that non-technical stakeholders can trust and act upon — while maintaining cost efficiency and compliance.

Solution

Designed and implemented agentic workflows with cost-optimized model selection, conducted cloud provider evaluations for scalability, and built a prompt engineering framework. Presented solutions in stakeholder workshops to drive adoption across business units.

Outcome

Improved productivity across multiple workflows. Made advanced AI tools accessible to non-technical users through intuitive interfaces and clear prompt frameworks. Established scalable, cost-efficient patterns for future AI adoption.

Key Takeaway

“In regulated environments, the hardest engineering challenge isn't the model — it's the trust framework. Cost-optimized model selection and transparent prompt design were key to stakeholder buy-in.”

Fraunhofer Society

Research / Public Sector · 2024

RAGKnowledge ManagementSecurityResearch

Private RAG Pipeline for Research Knowledge

Participated in building a private Retrieval-Augmented Generation pipeline using Fraunhofer's public data to improve AI response accuracy and knowledge accessibility.

PythonLangChainVector DBHybrid SearchGuardrails
View Source

Context

Research institutions generate vast quantities of publications, technical reports, and project documentation. Making this knowledge searchable, reliable, and accessible is a persistent challenge.

Challenge

Build a RAG system that maintains accuracy and security — resistant to hallucinations and prompt injection — while handling diverse document types and ensuring responses are grounded in verified institutional knowledge.

Solution

Led improvements in data ingestion and cleaning, retrieval processes, and guardrail design. Applied prompt engineering techniques to enforce factual grounding, reduce hallucinations, and strengthen robustness against prompt attacks — ensuring reliable and secure AI-powered knowledge management.

Outcome

Improved response accuracy and reduced hallucination rates. Established security patterns for AI systems handling sensitive research data, including defenses against prompt injection attacks.

Key Takeaway

“RAG quality is 80% data pipeline, 20% model. Investing heavily in data ingestion, cleaning, and chunking strategy paid off more than any prompt engineering technique. Security guardrails should be designed in from day one, not bolted on.”

PDF

Personal Project

HR Tech / AI Tooling · 2025

GenAIFull-StackHR TechDocument Generation

Hiro: AI-Powered Career Enhancement Platform

Built a GenAI-driven full-stack application to address inefficiencies in the application process by automating the adaptation of CVs, cover letters, and interview prep to specific job contexts.

ReactFastAPIPythonLLMsPDF/LaTeX Export

Context

Job seekers spend excessive time manually tailoring CVs and cover letters for each application. ATS systems filter out well-qualified candidates due to formatting and keyword mismatches. Interview preparation lacks personalization to specific roles.

Challenge

Create an AI platform that automates CV enhancement with ATS optimization, generates tailored cover letters, and provides context-aware interview preparation — while maintaining professional quality across recruiter-ready export formats.

Solution

Built a React + FastAPI application with ATS-optimized CV enhancement including keyword alignment and formatting compliance. Implemented tailored cover letter generation based on industry and literature review. Designed a responsive, accessible platform for both beginners and experienced professionals with seamless PDF and LaTeX export.

Outcome

Functional platform that dramatically reduces application preparation time. Demonstrates practical GenAI application for career optimization — addressing a universal pain point with production-quality tooling.

Key Takeaway

“The best AI tools solve friction, not complexity. ATS optimization required deep understanding of recruiter workflows, not just keyword matching. Export format quality (PDF, LaTeX) matters as much as content quality for user adoption.”

Screenshots
Hiro: AI-Powered Career Enhancement Platform screenshot 1
1 / 8

Personal Project

Education / AI Tooling · 2025

NLPEducationDocument IntelligenceAI Tooling

AI-Powered Academic Recognition & Planning Assistant

Built an AI assistant that automates academic credential recognition and study planning, helping international students navigate complex equivalency processes.

PythonLLMsNLPDocument ParsingFastAPI
View Source

Context

International students face significant bureaucratic challenges when transferring academic credentials between institutions and countries. Manual evaluation is time-consuming, error-prone, and inconsistent.

Challenge

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.

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

Functional tool 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

“Domain-specific AI tools don't need to be complex to be valuable. Understanding the user's pain point deeply — international students drowning in bureaucracy — shaped every design decision.”