Director/Sr. Manager, AI Inference Model Scaling

Cerebras Systems; Sunnyvale (CA); Hybrid; USD 260,000 - 340,000; Full time

Job summary

Cerebras Systems in Sunnyvale, CA is seeking an experienced engineering leader to build and scale the Inference Model Scaling organization. You will define the technical vision, strategy, and execution roadmap for a globally distributed team responsible for enabling foundation models on Cerebras hardware.

You will lead ML model compilation and optimization and develop high-performance kernels, partnering across compiler, runtime, cloud, hardware, product management, and AI research to advance

Qualifications

• 12+ years building compiler, ML systems, or infrastructure software.
• 5+ years leading engineering teams.
• Deep experience with modern compiler infrastructure (LLVM, MLIR, XLA, TVM, Torch FX, or similar).
• Strong understanding of graph compilation and optimization.
• Experience with Python and C++.
• Experience delivering production-quality software.
• Strong communication and cross-functional leadership skills.

Responsibilities

• Define the technical roadmap and strategy for the team.
• Establish technical direction across multiple teams and engineering leaders.
• Lead design reviews and establish engineering standards.
• Drive support for emerging LLM architectures and inference workloads.
• Hire, mentor, and grow a high-performing engineering team.
• Develop future technical leaders and managers.
• Drive organizational planning, headcount strategy, and investment priorities.
• Foster a strong engineering culture focused on execution, quality, and innovation.
• Scale engineering processes while maintaining execution velocity.
• Partner with Cloud Platform, ML, and Hardware teams in planning and delivering for end-to-end service enablement in Cloud and On-Premise settings.
• Work with Product Management to prioritize model enablement and customer needs.
• Collaborate closely with customers and solution architects on new model bring-up.
• Influence future hardware/software co-design through ML model enablement and optimization insights.
• Own planning, prioritization, and execution across multiple concurrent initiatives.
• Balance rapid model support with long-term ML Compiler architecture.
• Drive predictable delivery for strategic customer commitments.

Skills

Compiler infra

ML systems

Team leadership

LLVM/MLIR/XLA

Graph compilation

Python

C++

Production software

Cross-functional leadership

Education

BS/MS/PhD in CS/CE or related

Tools

LLVM

MLIR

XLA

TVM

Torch FX

Job description

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 with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.

Sunnyvale, CA or Toronto, Canada (Hybrid)

About the Team

The Inference Model Scaling team enables state-of-the-art foundation models and generative AI workloads to run efficiently on Cerebras' Wafer-Scale Engine (WSE). We build the compiler frontend, model transformation pipeline, graph optimization infrastructure, high-performance kernel enablement, and runtime integration that together make next-generation AI models execute with industry-leading performance.

The team works at the intersection of machine learning frameworks, compiler technologies, distributed systems, hardware architecture, and model optimization. We collaborate closely with hardware architects, runtime engineers, cloud platform teams, AI researchers, and strategic customers to rapidly bring new model architectures into production.

About the Role

We're looking for an experienced engineering leader to build and scale our Inference Model Scaling organization.

You will define the technical vision, organizational strategy, and execution roadmap for a globally distributed engineering team responsible for enabling the latest foundation models on Cerebras hardware. You will lead the engineering organization responsible for ML model compilation and optimization as well as development of high-performance kernels.

This role combines deep technical leadership with organizational excellence. You will partner across compiler, runtime, cloud infrastructure, hardware architecture, product management, and AI research teams while helping shape the future of AI inference at Cerebras.

Responsibilities

Technical Leadership

• Define the technical roadmap and strategy for the team.
• Establish technical direction across multiple teams and engineering leaders.
• Lead design reviews and establish engineering standards.
• Drive support for emerging LLM architectures and inference workloads.

Team Leadership

• Hire, mentor, and grow a high-performing engineering team.
• Develop future technical leaders and managers.
• Drive organizational planning, headcount strategy, and investment priorities.
• Foster a strong engineering culture focused on execution, quality, and innovation.
• Scale engineering processes while maintaining execution velocity.

Cross-Functional Collaboration

• Partner with Cloud Platform, ML, and Hardware teams in planning and delivering for end-to-end service enablement in Cloud and On-Premise settings
• Work with Product Management to prioritize model enablement and customer needs.
• Collaborate closely with customers and solution architects on new model bring-up.
• Influence future hardware/software co-design through ML model enablement and optimization insights.

Delivery & Execution

• Own planning, prioritization, and execution across multiple concurrent initiatives.
• Balance rapid model support with long-term ML Compiler architecture.
• Drive predictable delivery for strategic customer commitments.

Required Qualifications

• BS, MS, or PhD in Computer Science, Computer Engineering or related field.
• 12+ years building compiler, ML systems, or infrastructure software.
• 5+ years leading engineering teams.
• Deep experience with modern compiler infrastructure (LLVM, MLIR, XLA, TVM, Torch FX, or similar).
• Strong understanding of graph compilation and optimization.
• Experience with Python and C++.
• Experience delivering production-quality software.
• Strong communication and cross-functional leadership skills.

Preferred Qualifications

• Experience building compiler frontends for AI accelerators.
• Experience supporting PyTorch, JAX, TensorFlow, or ONNX.
• Experience with LLM inference or training systems.
• Familiarity with distributed compilation.
• Experience working with hardware architects.
• Experience leading teams through rapid growth.

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:

1. Build a breakthrough AI platform beyond the constraints of the GPU.
2. Publish and open source their cutting-edge AI research.
3. Work on one of the fastest AI supercomputers in the world.
4. Enjoy job stability with startup vitality.
5. Our simple, non-corporate work culture that respects individual beliefs.

Find out more about what it's like to work at Cerebras here!

Cerebras Systems is committed to creating an equal and diverse environment and is proud to be an equal opportunity employer. We celebrate different backgrounds, perspectives, and skills. We believe inclusive teams build better products and companies. We try every day to build a work environment that empowers people to do their best work through continuous learning, growth and support of those around them.

This website or its third-party tools process personal data. For more details, click here to review our CCPA disclosure notice.