Build machine learning inference APIs with Python and distributed systems expertise at Cerebras Systems, connecting GPU prefill with Cerebras decode.

As a Senior Software Engineer, you will develop production software across inference APIs, model integration, and request-routing services. Your work spans API design, model serving, and distributed systems, supporting consistent behavior across models and accelerator backends. You will own features through validation, rollout, and production operation.

Key Responsibilities

Design, implement, test, and operate inference API features

Integrate foundation models, tokenizers, and generation configuration

Coordinate routing between GPU prefill and Cerebras decode

Improve latency, throughput, and resource efficiency

Build tests,



benchmarks, metrics, and diagnostic tools

Requirements

At least five years of software engineering experience

Robust Python programming and proficiency in another service language

Production API design, validation, compatibility, and testing experience

Linux, containers, orchestration systems, and CI/CD experience

Bachelor’s degree or equivalent practical experience

Apply software engineering, API design, and distributed systems expertise to Cerebras inference platforms and production machine learning services.

📌 Senior ML Inference API Engineer (Winnipeg)
🏢 Fdetimes
📍 Winnipeg