Simulator Engineer

Job Description

Cerebras Systems builds the worlds largest AI chip, 56 times larger than GPUs. Our novel wafer-scale architecture provides the AI compute power of dozens of GPUs on a single chip, with the programming simplicity of a single device. This approach allows Cerebras to deliver industry-leading training and inference speeds and empowers machine learning users to effortlessly run large-scale ML applications, without the hassle of managing hundreds of GPUs or TPUs. Cerebras current customers include global corporations across multiple industries, national labs, and top-tier healthcare systems. In January, we announced a multi-year, multi-million-dollar partnership with Mayo Clinic, underscoring our commitment to transforming AI applications across various fields. In August, we launched Cerebras Inference, the fastest Generative AI inference solution in the world, over 10 times faster than GPU-based hyperscale cloud inference services. About The Role The Simulator team is responsible for a core internal tool that is used by many teams throughout the company to ensure the success of the next generation Cerebras WSE. The WSE is composed of an array of homogenous tiles. Each tile in composed of a compute element, that runs independent code and has access to its own memory, and a router connecting the compute element to the four neighboring tiles. The core of the simulator is a cycle accurate implementation of the tile. In this mode the simulator is used for design verification work, ensuring the quality of the ASIC design and the simulator implementation. The simulator also enables an array of tile to be combined into a 2D array. In this mode the simulator is used to develop kernel algorithms, where many tiles work together to implement a distributed operation, such as matrix multiplication, or an entire neural network, such as GPT-3 . Responsibilities Develop cycle accurate software simulators using C, C++ and Python to simulate precise system behavior of the Cerebras hardware. Enhance the simulator to extend to multiple architecture generations of the underlying wafer scale engine. Simulate and validate design verification coverage stimulus to build in functional and timing correctness into both the simulator and RTL design. Extend the simulator using advanced distributed compute frameworks like MPI and OpenMP to scale the simulator to a cluster of machines. Develop the fabric and interface solution for the architecture simulator which is used as a primary development platform for software development. Profile, debug and tune the simulator software for underlying micro architectures to help scale the simulations to cover the entire extent of the wafer scale engine. Develop and optimize infrastructure to interface the simulator with Cerebras test infrastructure and provide API s in Python to bridge the model to the PyTorch framework. Optimize the threading model and algorithms inherent to the simulator. Skills And Qualifications Bachelor s or masters degree in computer science or related field, or equivalent practical experience. Programming in C, C++ and Python. Data structures and algorithms. Demonstrated knowledge of computer architecture and microarchitecture. Software Development using Verilog or VHDL. Verification of microarchitecture designs using the Universal Verification Methodology (UVM) framework. Strong problem solving and debugging skills. Why Join Cerebras People who are serious about software make their own hardware. At Cerebras we have built a breakthrough architecture that is unlocking new opportunities for the AI industry. With dozens of model releases and rapid growth, we ve reached an inflection point in our business. Members of our team tell us there are five main reasons they joined Cerebras: Build a breakthrough AI platform beyond the constraints of the GPU. Publish and open source their cutting-edge AI research. Work on one of the fastest AI supercomputers in the world. Enjoy job stability with startup vitality. Our simple, non-corporate work culture that respects individual beliefs. .