Build machine learning APIs at Cerebras Systems using Python and distributed systems expertise to power heterogeneous AI inference services.
As a Senior Software Engineer, you will evolve the ML API layer across inference APIs, model integration, and request routing. The work spans API design, model serving, and distributed systems. You will translate model capabilities and customer requirements into reliable production software.
Key Responsibilities: Own inference features from design through production operation
Implement chat, streaming, sampling, tool calling, and structured outputs
Integrate models, tokenizers, templates, and generation configuration
Coordinate routing between GPU prefill and Cerebras decode
Build tests, benchmarks, metrics,
and diagnostic tools
Requirements: Five or more years of software engineering experience
Solid Python programming and proficiency in another production language
Experience evolving production APIs and distributed components
Experience with Linux, containers, Kubernetes, and CI/CD
Ability to diagnose correctness, reliability, and performance issues
Apply machine learning systems, API design, and distributed software expertise to advance Cerebras inference reliability and performance.