LlamaIndex Experts in Berlin

• Acted as technical consultant to optimize multi-layer ensemble models combining ResNet, CNN-BiGRU-Attention, and XGBoost.
• Guided implementation of a Logistic Regression meta-learner to solve class imbalance problems, achieving 92.86% accuracy and 0.9644 AUC on PTB-XL and Chapman-Shaoxing datasets.

• Pioneered first enterprise AI-SAP integration at ALDI SÜD, deploying AI-driven automation within one of retail's largest SAP S/4HANA programs, eliminating 50% of manual pre-cycle validation time and establishing replicable automation framework across 11 countries
• Led end-to-end SAP project lifecycle management for implementations across SAP S/4HANA and Manhattan Systems, supporting 7,300+ ALDI SÜD locations globally across Europe and Australia
• Served as primary executive liaison to C-level stakeholders across 11 countries for strategic SAP transformation programs
• Orchestrated automation, performance, and volume testing for critical releases, maintaining 99.9% system SLA compliance during peak retail periods
• Managed cross-functional international teams of 15+ specialists, delivering projects 20% faster than industry benchmarks
• Standardized SAP processes across 11 countries as part of one of retail's largest SAP implementations
• Directly managed €2M budget with 98% allocation accuracy across 12 concurrent projects
• Reduced SAP S/4HANA migration costs by 18% through strategic vendor contract renegotiations and optimization

• Leading 20+ staff in development, site reliability engineering, and architecture.
• Leading the group-wide agentic AI initiative (Norway, Poland, Germany).
• Hands-on solution architect and AI consultant for over 50% of my working time on client projects in the publishing sector – from local publishers to international corporations.
• Strategic consulting and technical implementation of AI workflow platforms (n8n, Workato).
• Developing prototypes for traditional, AI-based, and agentic AI workflows.

Geeks Ltd is a UK-based technology company; WordUp is its AI-driven language-learning product focused on personalized vocabulary learning and intelligent educational experiences.

• Coordinate AI product delivery across Product, Engineering, Data, Operations, and leadership, translating user needs into scoped initiatives, sequencing work, surfacing blockers, facilitating hand-offs, and communicating progress.
• Own search, recommendation, retrieval, and content-enrichment features end to end, from requirements and architecture through Python/FastAPI implementation, testing, deployment, monitoring, and rapid iteration.
• Developed low-latency retrieval, ranking, and personalization services using AWS, OpenSearch, DynamoDB, embeddings, and reusable APIs, achieving <1s latency, 22% higher engagement, and 12% higher premium conversion.
• Use AI coding assistants for codebase analysis, scaffolding, refactoring, tests, debugging, and documentation while reviewing every output for correctness, architectural fit, security, maintainability, and user value.
• Represent technical work in planning and stakeholder discussions, gather requirements first-hand, challenge priorities constructively, explain delivery trade-offs, and help teammates make outcome-focused decisions.

• Built an AI Research Assistant with RAG, LangChain, LangGraph, and OpenAI LLMs integrated with vector search.

• Built an AI Research Assistant with RAG, LangChain, LangGraph, and OpenAI LLMs integrated with vector search; cut research time by 30%.
• Designed custom retrieval workflows with LlamaIndex, building a ReAct-style agent for dynamic chunking; improved query accuracy by 18%.
• Researched and optimized embedding strategies, reducing retrieval cost/query by 15%.
• Developed RAG evaluation frameworks using RAGAS and Langsmith with custom datasets; improved coverage by 40%.
• Fine-tuned LLMs (LLaMA 2 on Vertex AI with custom inference containers, dynamic batching, and quantization); reduced inference latency by 25%.
• Integrated AI agents in LangGraph with short-term & long-term memory (Mem0); increased task completion rate by 20%.
• Created schema-aware synthetic data generators; fine-tuned downstream models achieving +12% F1 score.

• Introduced a serverless/event-driven platform, boosting deployment frequency from 3 to 40 per month
• Implemented an LLM-based fraud-detection proof of concept that flagged 92 % of suspicious transactions
• Built performance and DORA metrics dashboards adopted by the C-suite

• Designed and managed an upskilling academy for Deutsche Telekom.