Staff Software Engineer: AI Inference Infra & Kubernetes

Cerebras Systems; Sunnyvale (CA); On-site; USD 100,000 - 150,000; Full time

Job summary

Cerebras Systems in Sunnyvale, CA is seeking a Member of Technical Staff (Software Engineer) to implement infrastructure for high-performance, low-latency inference services. Applicants should have a Master’s degree in Computer Science or a related field and at least one year of software development experience. The position involves deploying Kubernetes services, optimizing resource allocation, and collaborating with machine learning engineers. Strong skills in Docker, Python, and infrastructure documentation are essential. The environment supports growth and diversity in tech.

Qualifications

• Master’s degree or foreign equivalent in Computer Science or a related field.
• At least 1 year of experience as a Software Developer or related occupation.

Responsibilities

• Implement infrastructure to support high‑performance, low‑latency inference service.
• Deploy and configure Kubernetes services to ensure scalability and reliability.
• Optimize resource allocation and auto‑scaling policies for inference demand.
• Integrate services with containerized environments using Docker.
• Ensure high availability and fault tolerance with multi‑region deployments.
• Develop Python scripts and APIs for data preprocessing and inference tasks.
• Collaborate with engineers to validate inference accuracy.
• Triage and resolve defects by analyzing logs and metrics.
• Debug issues related to model deployment and networking.
• Collaborate with teams to address performance regressions and scalability issues.
• Develop automated scripts to detect and mitigate failure modes.
• Author technical documentation for configurations and workflows.
• Work with product management on service interface requirements.
• Document defects and enhancements using tools like Jira and Git.
• Participate in release planning to align development with customer needs.

Skills

Docker

Kubernetes

Java

C++

ActiveMQ

Kafka

Python

Groovy

SQL

OracleDB

Redis

Git

Education

Master's degree in Computer Science or related field

Job description

Cerebras Systems in Sunnyvale, CA is seeking a Member of Technical Staff (Software Engineer) to implement infrastructure for high-performance, low-latency inference services. Applicants should have a Master’s degree in Computer Science or a related field and at least one year of software development experience. The position involves deploying Kubernetes services, optimizing resource allocation, and collaborating with machine learning engineers. Strong skills in Docker, Python, and infrastructure documentation are essential. The environment supports growth and diversity in tech.