Beschreibung

AI/ML engineer specializing in production-grade LLM and agentic systems for enterprise clients. At SAP I design agentic workflows, RAG pipelines, and conversational AI for B2B sales — my systems handle 20,000+ daily queries in production. M.Sc. Machine Learning & Data Science, Humboldt-Universität zu Berlin. 3+ years in German and international enterprise environments. Core strength: translating complex business problems into concrete AI architectures — from scoping through deployment and evaluation. Available for remote project engagements with European clients.

Sprachen

Englisch
Muttersprachlich oder zweisprachig
Deutsch
Konversationssicher

Arbeitsortpräferenzen

Nur remote

Führt Projekte hauptsächlich remote aus

SAP
Data & AI Specialist
SOFTWARE-HERSTELLER
August 2023 - Heute (3 Jahre)
Berlin, Germany
Architected an AI agent mapping customer business challenges → AI use cases + products, improving sales lead-matching accuracy by 25%.
Led 5-engineer team building RAG pipelines (LangChain, Python) for an internal GenAI chatbot — 20k+ daily queries, resolution rate +35%.
Designed DataHive, an agentic knowledge-retrieval service (Hugging Face + tool-using agents), cutting API response time by 40%.
Drove PoC → production delivery using SAP AI Core, multi-agent workflows, and similarity search.
Python Langchain RAG LLM SAP BTP
Ludwig Maximilian University of Munich
AI Research Scientist
FORSCHUNG
Oktober 2020 - Oktober 2022 (2 Jahre)
Munich, Deutschland
Built recommendation system and resource-allocation model over 10M+ data points.
Secured $200K via the German Chancellor Fellowship for research on AI in business-process automation.
Co-authored research on human–AI collaboration; covered by CNN and international media.
Machine learning Python NLP Recommender Systems Pytorch
Trip.com Group
Senior Data Engineer
REISEN & TOURISMUS
Juni 2018 - Oktober 2020 (2 Jahre und 4 Monate)
Shanghai, China
Built Python/Node.js recommendation engine for call-center task allocation — throughput +50%, latency −30%.
Automated content classification with computer vision, reducing manual review effort by 40%.
Python Node.js Recommendation systems Computer Vision SQL