Shape AI inference software at Cerebras Systems with Python, model serving, and production API experience across accelerator backends.

This Senior Software Engineer role focuses on making disaggregated inference accessible, reliable, and consistent. You will work across model integration, request-routing services, and inference APIs. Your work supports streaming, multimodal inputs, tool use, structured outputs, and model configuration.

Key Responsibilities

Design and operate features for chat and text generation

Maintain request and response semantics across inference backends

Extend integrations with vLLM, PyTorch, and Hugging Face

Improve latency, throughput, batching, and resource efficiency

Investigate incidents and strengthen resilience and response

Requirements

Five or more years owning production software components

Python strength plus Go, C++, Rust, or another service language

Experience spanning service, framework, runtime, or infrastructure boundaries

Familiarity with REST, gRPC, or streaming protocols

Solid communication, technical leadership, and mentoring experience

Bring production software judgment to Cerebras AI inference through model serving, API evolution, routing, and performance improvement.

📌 Senior AI Inference Software Engineer (Winnipeg)
🏢 Cerebras
📍 Winnipeg