Thomas Saueressig Appointed SAP Chief Customer Officer
WALLDORF — The new Customer Value Group Board area will strengthen SAP’s customer-centric operating model.
WALLDORF — SAP SE (NYSE: SAP) today announced the creation of the new Customer Value Group, bringing together the Customer Success and Customer Services & Delivery organizations, effective April 1.
The new Board area is designed to strengthen SAP’s customer-centric operating model by delivering seamless, end-to-end experience from initial engagement through long-term value realization.
The Customer Value Group will be led by Thomas Saueressig (40), whose role expands to Chief Customer Officer. In this capacity, he will oversee the full customer journey, aligning selling, delivery, services and support driving adoption, renewal and expansion of SAP’s cloud and AI-powered solutions. SAP Extended Board members Jan Gilg and Manos Raptopoulos will report directly to Saueressig and continue to co-lead the Customer Success organization.
“In a business where adoption and renewal define success, the lines between selling and delivering disappear,” said Christian Klein, CEO of SAP SE. “Bringing Customer Success and Customer Services & Delivery together is the right move now for our customers and for SAP, as we go all in on AI. Thomas combines deep product expertise with strong experience in services and customer delivery, and he has earned the trust of our customers and teams. I am convinced that under his leadership, this new organization will drive lasting customer value across the full journey.”
Saueressig is a member of the Executive Board of SAP SE, having joined SAP in 2004 and been appointed to the Board in 2019. Prior to his new role, he led the Customer Services & Delivery Board area with global responsibility for long-term customer value in the cloud, including professional services, customer innovation services, support and SAP’s cloud infrastructure and operations. Earlier, he headed SAP Product Engineering, overseeing SAP’s complete application portfolio, and served as Chief Information Officer, driving SAP’s internal cloud-first transformation. He holds a degree in Business Information Technology and a joint Executive MBA from ESSEC Business School and Mannheim Business School.
Visit the SAP News Center. Get SAP news via LinkedIn and Bluesky.
Media Contact:Marcus Winkler, +49 6227 7-67497, [email protected], CETSAP Press Room; [email protected]
This document contains forward-looking statements, which are predictions, projections, or other statements about future events. These statements are based on current expectations, forecasts, and assumptions that are subject to risks and uncertainties that could cause actual results and outcomes to materially differ. Additional information regarding these risks and uncertainties may be found in our filings with the Securities and Exchange Commission, including but not limited to the risk factors section of SAP’s 2025 Annual Report on Form 20-F.© 2026 SAP SE. All rights reserved.SAP and other SAP products and services mentioned herein as well as their respective logos are trademarks or registered trademarks of SAP SE in Germany and other countries. Please see https://www.sap.com/copyright for additional trademark information and notices.
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
model
30 Days of Building a Small Language Model — Day 1: Neural Networks
Welcome to day one. Before I introduce tokenizers, transformers, or training loops, we start where almost all modern machine learning starts: the neural network. Think of the first day as laying down the foundation you will reuse for the next twenty-nine days. If you have ever felt that neural networks sound like a black box, this post is for you. We will use a simple picture is this a dog or a cat? and walk through what actually happens inside the model, in plain language. What is a neural network? A neural network is made of layers. Each layer has many small units. Data flows in one direction: each unit takes numbers from the previous layer, updates them, and sends new numbers forward. During training, the network adjusts itself so its outputs get closer to the correct answers on example
Monarch v3: 78% Faster LLM Inference with NES-Inspired KV Paging
TL;DR: We implemented NES-inspired memory paging for transformers. On a 1.1B parameter model, inference is now 78% faster (17.01 → 30.42 tok/sec) with nearly zero VRAM overhead. The algorithm is open source, fully benchmarked, and ready to use. The Problem KV cache grows linearly with sequence length. By 4K tokens, most of it sits unused—recent tokens matter far more than old ones, yet we keep everything in VRAM at full precision. Standard approaches (quantization, pruning, distillation) are invasive. We wanted something simpler: just move the old stuff out of the way. The Solution: NES-Inspired Paging Think of it like a Game Boy's memory banking system. The cache is split into a hot region (recent tokens, full precision) and a cold region (older tokens, compressed). As new tokens arrive,
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Models
30 Days of Building a Small Language Model — Day 1: Neural Networks
Welcome to day one. Before I introduce tokenizers, transformers, or training loops, we start where almost all modern machine learning starts: the neural network. Think of the first day as laying down the foundation you will reuse for the next twenty-nine days. If you have ever felt that neural networks sound like a black box, this post is for you. We will use a simple picture is this a dog or a cat? and walk through what actually happens inside the model, in plain language. What is a neural network? A neural network is made of layers. Each layer has many small units. Data flows in one direction: each unit takes numbers from the previous layer, updates them, and sends new numbers forward. During training, the network adjusts itself so its outputs get closer to the correct answers on example
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!