Staff Software Engineer, AI Inference Platform

Cerebras; Sunnyvale (CA); On-site; USD 140,000 - 200,000; Full time

Job summary

Cerebras Systems is seeking a Software Engineer to build and maintain high-performance, low-latency inference infrastructure. You will deploy scalable inference services, optimize auto-scaling, and integrate with Docker/Kubernetes in production environments.

You will collaborate with ML engineers to validate accuracy and performance, triage defects, and document configurations and APIs for internal teams and customers. This role emphasizes reliability, observability, and efficient resource use.

Qualifications

• Master's degree in Computer Science or a related field.
• 1 year of experience as Software Developer or related role.
• Employer accepts full-time or equivalent part-time experience gained before, during, or after graduate studies.

Responsibilities

• Implement infrastructure to support high-performance, low-latency inference service.
• Deploy and configure Kubernetes services to ensure scalability and reliability of inference workloads.
• Optimize resource allocation and auto-scaling policies to handle variable inference demand while minimizing operational costs.
• Integrate inference services with containerized environments using Docker and Kubernetes for orchestration.
• Ensure high availability and fault tolerance by implementing multi-region deployments and disaster recovery strategies.
• Develop Python-based scripts and APIs to streamline data preprocessing, inference execution, and post-processing for real-time inference tasks.
• Collaborate with machine learning engineers to validate inference accuracy and performance against functional and latency requirements.
• Triage and resolve defects in the service by analyzing logs, metrics, and distributed traces.
• Debug issues related to model deployment, container orchestration, or networking configurations, documenting steps to reproduce and root-cause defects.
• Collaborate with cross-functional teams to address performance regressions, scalability issues, or integration failures in the inference pipeline.
• Develop automated scripts to detect and mitigate common failure modes, improving system reliability.
• Author detailed technical documentation for infrastructure configurations, inference workflows, and APIs, ensuring clarity for internal teams and external customers.
• Work with product management and user experience teams to define requirements for inference service interfaces, including configuration, monitoring, and event logging.
• Document and track defects, enhancements, and release notes using tools like Jira and Git, ensuring version control and traceability.
• Participate in release planning and prioritization discussions to align infrastructure development with customer needs and business objectives.

Skills

Docker and Kubernetes

Java or C++

ActiveMQ and Kafka

Python or Groovy

JavaScript or TypeScript

Linux

SQL, OracleDB, and Redis

Git

Education

Master's degree in Computer Science or related field

Job description

Cerebras Systems is seeking a Software Engineer to build and maintain high-performance, low-latency inference infrastructure. You will deploy scalable inference services, optimize auto-scaling, and integrate with Docker/Kubernetes in production environments.

You will collaborate with ML engineers to validate accuracy and performance, triage defects, and document configurations and APIs for internal teams and customers. This role emphasizes reliability, observability, and efficient resource use.