About
I build AI systems that have to work where it counts: reliable, explainable, and safe enough for the real world.
At SAP I design and ship enterprise retrieval-augmented generation: a production RAG framework over the SAP Help Portal and case-management data, the prompt framework behind several SAP AI services, and the auto prompt-tuning that taught those pipelines to retrieve the right document instead of just writing fluent answers. Most of my focus is the load-bearing, unglamorous part: secure prompting against injection, reasoning chains for explainability, and model lifecycle on Kubeflow and CI/CD.
Before SAP I researched at DFKI, on computer-vision OCR and NER inside a Trusted Research Environment for sensitive health records, and wrote my Master's thesis, SIGN-LLM, generating expressive 3D sign-language motion from text. Earlier, four years as a software engineer at EPAM shipping full-stack and ML systems. I hold an M.Sc. in Computer Science from RPTU Kaiserslautern.
Experience
-
2024 – present · Germany
Data Scientist · SAP
Enterprise RAG, prompt frameworks, secure prompt engineering.
-
2023 – 2024 · Germany
Machine Learning Engineer · SAP
Human-feedback loops and evaluation for RAG search.
-
2022 – 2023 · Germany
Research Assistant · DFKI
CV-OCR and NER; secure ML for sensitive health records.
-
2018 – 2022 · India
Senior Software Engineer · EPAM Systems
Full-stack and ML systems for financial & enterprise clients.
-
Early career · India
Product Development Intern · Adobe Systems
Performance work on the Live Edit Service.
Capabilities
- AI / ML
- LLMs · RAG · NLP · Computer Vision · NER · OCR · Deep Learning · Secure ML
- Languages
- Python · Java · Julia · C
- Frameworks
- PyTorch · TensorFlow · Hugging Face · spaCy · BERT · FastAPI · Django · Spring · Angular
- Cloud / MLOps
- AWS · GCP · Azure · Kubernetes · Kubeflow · Docker · CI/CD · Jenkins
- Data
- PySpark · PostgreSQL · MongoDB · SQL · OracleDB · ArangoDB · Power BI