JOB POSTING INFORMATION
Position Type:	Professional Experience Year Co-op (PEY Co-op: 12-16 months)
Job Title:	Performance Engineer
Job Location:	Toronto
Job Location Type:	Flexible
If working on site, can you provide a copy of your COVID-19 safety protocols?:	No
Number of Positions:	1
Salary:	$42.00 hourly for 40.0 hours per week
Start Date:	05/06/2024
End Date:	04/25/2025
Job Function:	Engineering
Job Description:	Cerebras Systems has pioneered a groundbreaking chip and system that revolutionizes deep learning applications. Our system empowers ML researchers to achieve unprecedented speeds in training and inference workloads, propelling AI innovation to new horizons. The Condor Galaxy 1 (CG-1), unveiled in a recent announcement, stands as a testament to Cerebras' commitment to pushing the boundaries of AI computing. With a staggering 4 ExaFLOP processing power, 54 million cores, and 64-node architecture, the CG-1 is the first of nine powerful supercomputers to be built and operated through an exclusive partnership between Cerebras and G42. This strategic collaboration aims to redefine the possibilities of AI by creating a network of interconnected supercomputers that will collectively deliver a mind-boggling 36 ExaFLOPS of AI compute power upon completion in 2024. Cerebras is building a team of exceptional people to work together on big problems. Join us! About The Role As a member of our Performance team, you will work with leaders from industry and academia at the intersection of hardware and software, to develop state-of-the-art solutions for emerging problems in AI compute. We’re looking for a performance engineer to estimate and optimize end-to-end performance for the hardware, software stack, and workload of Cerebras’ new AI-optimized system.
Job Requirements:	Responsibilities Develop models for the hardware, software stack, and workload to estimate end-to-end performance Develop tools to analyze performance and identify bottlenecks and optimization opportunities Work with the hardware and software design teams to analyze and optimize workload performance through: Understanding and improving existing algorithms Micro-code optimizations (Accelerator Software) Optimizing inefficiencies in the performance of the cluster of machines feeding the accelerator. Designing new features to circumvent existing bottlenecks Requirements Background in Computer Science, Electrical Engineering, or equivalent, particularly with focus in computer architecture Background in performance analysis on CPUs, GPUs, and parallel architectures Experience with end-to-end workload analysis from low level assembly instruction code to high level distributed algorithms is very desirable Programming/scripting expertise in C/C++ and Python
Preferred Disciplines:	Computer Engineering Computer Science Electrical Engineering Engineering Science (Biomedical) Engineering Science (Electrical and Computer) Engineering Science (Machine Intelligence) Engineering Science (Physics)
All Co-op programs:	No
Targeted Co-op Programs:	Targeted Programs Professional Experience Year Co-op (12 - 16 months)

APPLICATION INFORMATION
Application Deadline:	Dec 1, 2023 11:59 PM
Application Receipt Procedure:	Online via system
U of T Job Coordinator:	Yasmine Abdelhady

ORGANIZATION INFORMATION
Organization:	Cerebras Systems
Division:	Computer Science
Website:	https://cerebras.net/

ADDITIONAL INFORMATION
Length of Workterm:	FLEXIBLE PEY Co-op: 12-16 months (range)