Biography
Prof Noa Zilberman leads the Computing Infrastructure Group at the Department of Engineering Science.
Her research focuses on the integration of micro-level architectures and macro level, large scale networked-systems. Zilberman's research interests range from computer architecture, programmable hardware and networking to data science, with a specific interest in the combination of multiple disciplines (and a touch of measurements). Current research interests include sustainable computing infrastructure, systems for AI, networked-systems architectures, in-network computing and in-network machine learning, performance measurements, and others.
Before joining Oxford, Prof Zilberman was a Fellow and an Affiliated Lecturer at the University of Cambridge' Department of Computer Science and Technology. Prof Zilberman has over 15 years of industrial experience. In her last role before moving to academia, she was a Senior Principal chip architect in Broadcom's Network Switching group.
Most Recent Publications
PlanPi: in-network machine learning via p4c-dpdk
PlanPi: in-network machine learning via p4c-dpdk
Hardware-managed heterogeneous high-bandwidth memory and flash in LLM inference systems
Hardware-managed heterogeneous high-bandwidth memory and flash in LLM inference systems
In-Network Market Prediction Using Machine Learning and Limit Order Books
In-Network Market Prediction Using Machine Learning and Limit Order Books
HyNIC: hybrid in-network inference for line-rate anomaly detection on smartNICs
HyNIC: hybrid in-network inference for line-rate anomaly detection on smartNICs
Real-time intrusion detection for IoMT with in-network inference on SmartNICs
Real-time intrusion detection for IoMT with in-network inference on SmartNICs
Research Interests
- Open source networking and computing research
- Sustainable computing
- Programmable platforms
- High performance networked systems
- Network switching architectures
- Computing architectures
- In-network computing
- Queuing and buffering
- Memory management
- Performance analysis
- High speed interfaces
Research Group
Most Recent Publications
PlanPi: in-network machine learning via p4c-dpdk
PlanPi: in-network machine learning via p4c-dpdk
Hardware-managed heterogeneous high-bandwidth memory and flash in LLM inference systems
Hardware-managed heterogeneous high-bandwidth memory and flash in LLM inference systems
In-Network Market Prediction Using Machine Learning and Limit Order Books
In-Network Market Prediction Using Machine Learning and Limit Order Books
HyNIC: hybrid in-network inference for line-rate anomaly detection on smartNICs
HyNIC: hybrid in-network inference for line-rate anomaly detection on smartNICs
Real-time intrusion detection for IoMT with in-network inference on SmartNICs
Real-time intrusion detection for IoMT with in-network inference on SmartNICs
DPhil Opportunities
I am always looking for outstanding graduate students to join the team, particularly those with an interest in programmable hardware, networking, systems and computer architecture. I would encourage potential students to contact me by email before applying.
Research Group
Most Recent Publications
PlanPi: in-network machine learning via p4c-dpdk
PlanPi: in-network machine learning via p4c-dpdk
Hardware-managed heterogeneous high-bandwidth memory and flash in LLM inference systems
Hardware-managed heterogeneous high-bandwidth memory and flash in LLM inference systems
In-Network Market Prediction Using Machine Learning and Limit Order Books
In-Network Market Prediction Using Machine Learning and Limit Order Books
HyNIC: hybrid in-network inference for line-rate anomaly detection on smartNICs
HyNIC: hybrid in-network inference for line-rate anomaly detection on smartNICs
Real-time intrusion detection for IoMT with in-network inference on SmartNICs
Real-time intrusion detection for IoMT with in-network inference on SmartNICs
