Senior ML API Engineer – Real-Time Inference Leader

Cerebras Systems; Sunnyvale (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Cerebras Systems is building a new generation of disaggregated AI inference systems and is hiring a Senior Software Engineer to shape the ML API layer that makes this heterogeneous serving system accessible and reliable. You will own features across inference APIs, model integration, and request-routing, delivering a consistent experience across models and backends.

You will work with model enablement, compiler, runtime, cloud infrastructure, product, and customers, translating evolving model

Qualifications

• 5+ years of software engineering experience with production services or distributed systems.
• Experience designing and delivering features spanning multiple components and APIs.
• Production APIs with validation, error handling, compatibility, and testing.
• Experience across service, framework, runtime, or infrastructure boundaries.
• Operating services on Linux with containers, Kubernetes, and CI/CD.

Responsibilities

• Own features end to end for chat completions, text generation, streaming, and model configuration.
• Lead multi-component delivery with clear design docs and milestones.
• Deliver consistent API behavior across multiple backends and interfaces.
• Enable new models and capabilities within the serving platform.
• Integrate serving components with frameworks like PyTorch, Hugging Face, and vLLM.
• Improve reliability with tests, metrics, tracing, and incident response.
• Raise engineering quality through reviews, mentorship, and collaboration.

Skills

Python

Go

C++

Rust

Distributed systems

API design

Education

Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or related field

Tools

REST

gRPC

Kubernetes

Job description

Cerebras Systems is building a new generation of disaggregated AI inference systems and is hiring a Senior Software Engineer to shape the ML API layer that makes this heterogeneous serving system accessible and reliable. You will own features across inference APIs, model integration, and request-routing, delivering a consistent experience across models and backends.

You will work with model enablement, compiler, runtime, cloud infrastructure, product, and customers, translating evolving model