Simulation Engineer

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. This architecture allows Cerebras to deliver industry-leading training and inference speeds; over 10 times faster than GPU-based hyperscale cloud inference services.

This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation.

Cerebras works with the leading model labs, global enterprises, and cutting-edge AI-native startups. OpenAI recently announced a multi-year partnership https://openai.com/index/cerebras-partnership/ with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.

About The Role

As a Software Engineer on the Simulator Team (New College Grad), you will help build and improve the core simulation infrastructure for the next-generation Cerebras Wafer-Scale Engine (WSE). This role spans multiple simulator efforts, including functional simulation and pipeline-accurate simulation, based on team priorities and product needs.

The Simulator team builds foundational internal tools used across Cerebras for hardware and software co-development. These tools give kernel developers, compiler and runtime teams, architects, and design verification engineers visibility into both correctness and performance. Your work will help teams validate architectural behavior, understand performance tradeoffs, and move faster as new systems come online.

You will contribute to simulator architecture, model development, tooling, testing, and runtime optimization, working closely with cross-functional teams to keep our simulators accurate, scalable, and useful in day-to-day development.

Responsibilities

• Develop and maintain simulator infrastructure in C++ for next-generation WSE systems.

• Contribute to both functional simulation (architectural correctness, instruction behavior, and state and memory semantics) and pipeline-accurate simulation (execution behavior, bottleneck analysis, and performance visibility).

• Build features and tooling that improve kernel developer visibility into correctness and performance.