- Develop, test, and maintain accurate performance models for system IPs, ranging from a memory subsystem to an interconnect for multiple processing elements or for die-to-die connection
- Collaborate with multi-site engineering teams to make data-driven decisions on many of their current engineering issues
- Collaborate with hardware design engineers to prune the design space of next generation NPU designs, understanding performance opportunities on current processors and investigate potential micro-architectural enhancement
- Collaborate with software engineers to enable various levels of software development at the very early stage
- Support hardware design engineers to solve potential performance issues in design verification flows
- Develop systems and performance analysis tools necessary for performance correlation and verification workflows
- Masters, PhD, or equivalent experience in Computer Engineering, Electrical Engineering, or related field
- Knowledge of on-chip bus protocols such as AMBA, coherency flows, interconnects, memory subsystems
- Demonstrated ability in system performance modelling, workload analysis, system performance bottleneck debug and analysis
- Strong problem solving and analytical skills
- Strong programming skills with good understanding of object-oriented languages such as C++/Python
- Knowledge of performance or functional modelling of NPUs, CPUs, or GPUs
- Excellent collaboration skills
- Outstanding written and verbal communications
- Knowledge of Machine Learning concepts and ML hardware accelerators
- Prior experience in simulator development
- Proficiency in computer/SoC architecture and performance trade-offs
- Knowledge of a system modelling/simulation technology, such as SystemC, Gem5, Simics, QEMU and etc
- Knowledge of Verilog and/or VHDL and experience with simulators and waveform debugging
- Familiarity with RISC-V architectures and instruction sets
- Knowledge of script languages
- Application review > 1st Interview > 2nd Interview (technical) > 3rd Interview
System Performance Engineer - Cambridge, United Kingdom - Neubla
Description
Job Description
System Performance Modelling Engineer in Cambridge, UK
About Neubla
As pioneers of innovative neural computing, Neubla is transforming the future of computing by bringing the enormous potential of neural computing to the highest performance in most data-intensive applications. Neubla is made up of people with expertise and lots of experience in many different fields such as AI, semiconductor design, and compilers. At Neubla, you can work in a rapidly changing environment where your new ideas will become innovative products, services, and customer experiences, working with talented colleagues. Neubla offers a competitive package with benefits, including health insurance, a pension scheme, employee wellness support, and a variety of snacks in the office
Summary
We're looking for an exceptional individual with a passion to learn about ground-breaking AI architectures and who is eager to build highly optimised models for performance and functional simulation.
Performance and functional simulation are critical tools for architecture exploration, and it has been used to make many important decisions of various systems. In this highly visible role, you will collaborate closely with multi-site HW and SW teams to investigate and evaluate new micro-architectural ideas and design trade-offs to shape the system features of the next generation AI accelerator by developing, verifying, and using performance models for data-driven architectural exploration and validation.
Job Description
Qualifications
Preferred Qualifications
The Process