Senior ML API Engineer - High-Speed AI Inference

Cerebras; United States; Remote; USD 160,000 - 260,000; Full time

Job summary

Cerebras Systems, a leader in AI hardware, seeks a Senior Software Engineer to shape the ML API layer of our disaggregated inference stack. You will own features across chat completions, text generation, streaming, and model integration, delivering a reliable, scalable experience.

This hands-on role requires collaboration with model enablement, compiler, runtime, cloud, product, and customers, translating evolving capabilities into robust designs and production-ready code.

Qualifications

• Hands-on experience designing and implementing ML inference APIs.
• Proficiency in distributed systems and scalable services.
• Experience translating model capabilities into production features.

Responsibilities

• Own end-to-end features for chat, text generation, streaming, and model integration.
• Lead multi-component delivery with cross-team collaboration.
• Ensure consistent API behavior across backends and maintain backward compatibility.
• Enable new models and capabilities by integrating tokenizers, templates, and configurations.

Skills

API design

Distributed systems

ML systems

Hands-on coding

Job description

Cerebras Systems, a leader in AI hardware, seeks a Senior Software Engineer to shape the ML API layer of our disaggregated inference stack. You will own features across chat completions, text generation, streaming, and model integration, delivering a reliable, scalable experience.

This hands-on role requires collaboration with model enablement, compiler, runtime, cloud, product, and customers, translating evolving capabilities into robust designs and production-ready code.