NVIDIA

System Software Architecture Researcher - PhD Program

In short

36-month fully funded PhD position at NVIDIA (with enrollment at a partner University) researching accelerated data-center architectures, as part of the EU Horizon Europe-funded SOVEREIGN-6G project. The role focuses on DPU-based load balancing for storage servers accessed through high-capacity network interface cards, spanning networking, security, RDMA and storage. Requires a Master's in Electrical Engineering, Computer Science or Computer Engineering, strong C/C++/Python skills, low-level Linux knowledge, and ideally familiarity with NVMe-oF and RDMA ibverbs.

About the Role
NVIDIA is searching for a PhD candidate to join our growing software architecture team in the context of the project SOVEREIGN-6G funded by the European Commission under the Horizon Europe research program. The ideal candidate will be conducting innovative research at the intersection of Networking, Security, and Communications, and working alongside top authorities in these fields. With incredible resources at your disposal, you will be able to impact, contribute and advance these exciting domains. Topics include but are not limited to remote direct memory access, hardware offloading and acceleration, AI for networking and security, storage management, cryptography, and architecture. With its unique open culture, NVIDIA is one of the best industry labs to do Accelerated Computing research.
DPU Data-Processing Units are the smallest form of a data center, and provide the foundation to implement accelerated computing, where both processing and networking experience a performance boost through the utilization of dedicated processors. DPUs started out as the engine for accelerated networking, but now they can run AI inference and training on-board, deep packet inspection and cryptography accelerations among others thanks to onboard GPUs and acceleration engines. In particular, this doctoral position will look at load balancing on storage servers access through high-capacity network interface cards.
Join us to research next-generation accelerated data-center architectures in a unique PhD program with NVIDIA partnership. The program is 36 months long and it includes enrollment in a PhD program at one of our partner Universities.
What You'll Be Doing
•Be at the forefront of modern data center research
•Partner and collaborate with forward-thinking industry leaders and external researchers
•Participate and speak at conferences and events
•Publish original research
•Work with intelligent networking machines powered by AI systems that can learn, reason and interact with other network components
What We Need to See
•Must hold a Master's in Electrical Engineering, Computer Science or Computer Engineering
•General computer science background, preferably in algorithm design, system programming, networking, operating system, and computer architecture
•Strong programming (C/C++/Python) and software development skills
•Low-level Linux
•Remote storage knowledge (e.g. NVMe-oF), RDMA ibverbs and operating systems research are a plus
•Good communications skills

Stop applying.
Get referred.

$10 in free credits

In just 60 seconds, fully on autopilot — Eraldt's AI agents read your CV, map the roles you fit, find live vacancies and the people who can refer you, write personal emails, and get you referred.

This isn't an application: your CV doesn't go to the company, and we don't promise a referral for this exact role.

Discover who else lands interviews on autopilot