I build LLM-powered agent systems, RAG pipelines, and the scalable services that keep them honest in production.
Currently an AI & Cloud Engineer at AI Marketplace GmbH and an M.Sc. Computer Science candidate at Paderborn University, working on multi-agent orchestration, explainable AI, and knowledge graphs.
Selected Experience
2024 to Present
AI & Cloud Engineer
AI Marketplace GmbH · Working student, 20 hrs/week · Paderborn
Agent Engine: scalable microservices
Drove a 300%+ improvement in microservice response times by architecting a Redis-backed scaler-worker system, with no degradation in output quality.
Designed a 3-mode orchestrator agent, Plan, Ask, and Accept All, offering flexible human-in-the-loop control across autonomous and supervised execution modes.
Led the architecture of a 13+ agent orchestration framework in LangGraph for automated 3D-structure creation, modification, and deletion, a novel application of multi-agent systems.
Microsoft Copilot RAG System, Client: prostep ivip
Led end-to-end design and deployment of a Copilot RAG system with role-based access control, processing 3,000+ documents and serving users directly inside MS Teams.
Engineered a sandboxed Python execution environment running user code in isolated Docker containers, eliminating remote code execution risk.
2023 to 2024
Student Research Assistant
DICE Research Group · Paderborn University
Benchmarked 6 open-source LLMs (Mistral, Mixtral, Llama 2/3, Zephyr) and achieved 90%+ accuracy on material-science tasks post fine-tuning, on par with state-of-the-art proprietary models.
Mapped hundreds of research papers and material-science URIs to the Springer knowledge graph, improving RAG workflow efficiency by 25%.
Deployed and enriched a SPARQL endpoint over the KG using Wikipedia substance and property data, driving a 30% lift in data organization quality.
2020 to 2022
Python Instructor
Cue Learn & Self-employed · India · 80+ students, 4 countries
Taught Python and game development (pygame, tkinter) to 80+ students across the US, UK, Canada, and Switzerland, with a 95% satisfaction rate.
Earned Star Teacher recognition within 3 months of joining Cue Learn, the fastest in the cohort.
Publication
ESWC 2024 · Posters & Demos · Springer LNCS
CLASS MATE: Cross-Lingual Semantic Search for Material Science Driven by Knowledge Graphs
First contribution to cross-lingual semantic search in material science. Built a KG with multilingual entity labels for chemical substances, implemented a symbolic similarity-based NER algorithm, and shipped a demo retrieving information from the KG and LOD sources across languages.
A. Perevalov, J. Chinchghare, M. Krishna, S. Sharma, A. N. Lal, A. Deshwal, A. Both, A.-C. Ngonga Ngomo
Pitching at Makathon #XCHANGE4INDUSTRY · Paderborn · Dec 2025
Makathon #XCHANGE4INDUSTRY
Fraunhofer IEM · Team of 5 ·1st place, €3,000
Solved two real-world problems for Werkzeugbau Berger GmbH: a high-temperature IoT sensor module for injection moulds enabling predictive maintenance, and Digital Vault, a centralized, versioned document platform used by Berger, suppliers, and clients.
Vibathon
Google Developer Group ·1st place
Built a language-agnostic AI agent that calls doctors on the user's behalf, schedules appointments, and syncs with the calendar, fully autonomous end-to-end.
Projects
Fact-Checking Engine over Wikipedia KG
RDF · SPARQL · Python
Validation engine leveraging the Wikipedia knowledge graph, achieving 92% accuracy on claim verification.
Explaining GNNs on Heterogeneous Graphs
PyTorch Geometric · Captum
Explainability system for graph neural networks reaching 88% explanation accuracy in predicted links.
Requirement Doc Generation with Generative AI
FastAPI · Noctua HPC
Led backend for a 5-person team; cut project runtime by 70% via code optimization and fine-tuning on Paderborn's supercomputer.
ASL Learning with Computer Vision
OpenCV · MediaPipe
Gesture-recognition app teaching American Sign Language at 95% detection accuracy; led a team of three.
Education
2023 to Present
M.Sc. Computer Science
Paderborn University · Paderborn, Germany
Machine Learning · Explainable AI · Knowledge Graphs · Large Language Models · Deep Learning · Unsupervised Learning (R). Master's thesis in progress.
2017 to 2021
B.Tech Computer Science & Engineering
KCC Institute of Technology & Management (AKTU) · India
Toolbox
Languages
Python · SQL · SPARQL · R · C · RDF / Turtle · JavaScript
LLMs · RAG · Multi-Agent Systems · Knowledge Graphs · Explainable AI · Computer Vision · NLP
Languages (human)
Hindi (native) · English (C1) · German (A1.2)
Let's build something unreasonably useful.
If you're hiring for AI engineering, applied research, or platform work on LLM systems, I'd love to hear from you. The fastest way to reach me is email.
