Remote Principal Engineer, AI Inference Reliability

Description:

• Cerebras Systems builds the world's largest AI chip, which is 56 times larger than GPUs.
• The company's wafer-scale architecture provides the AI compute power of dozens of GPUs on a single chip, simplifying programming.
• Cerebras delivers industry-leading training and inference speeds, enabling users to run large-scale ML applications without managing multiple GPUs or TPUs.
• Current customers include global corporations, national labs, and top-tier healthcare systems.
• The company has announced a multi-year partnership with Mayo Clinic to transform AI applications across various fields.
• Cerebras launched the fastest Generative AI inference solution in the world, which is over 10 times faster than GPU-based hyperscale cloud inference services.
• The Cerebras Inference team aims to deliver the most performant, secure, and reliable enterprise-grade AI service.
• The role involves driving reliability strategy and execution across the inference stack, including client SDKs and multi-region deployments.

Requirements:

• A bachelor's or master's degree in computer science or a related field is required.
• Candidates must have 7+ years of experience in backend, infrastructure, or reliability engineering for large-scale distributed systems.
• Strong programming skills in at least one popular backend programming language such as Python, C++, Go, or Rust are necessary.
• Deep experience with reliability principles, including SLO/SLI/SLA design, incident response, and postmortem culture is essential.
• Excellent communication and cross-functional leadership skills are required.
• Prior experience building large-scale AI infrastructure systems is a bonus.

Benefits:

• Employees have the opportunity to build a breakthrough AI platform beyond the constraints of the GPU.
• Team members can publish and open source their cutting-edge AI research.
• Employees work on one of the fastest AI supercomputers in the world.
• The company offers job stability combined with startup vitality.
• Cerebras promotes a simple, non-corporate work culture that respects individual beliefs.