Member of Technical Staff Software Engineer
Cerebras Systems, Inc.Visit Cerebras Systems, Inc. website
Cerebras builds wafer-scale AI computing systems and a cloud inference platform for training, fine-tuning, and serving AI models.
Sunnyvale, California, United States
About Cerebras Systems, Inc.
Cerebras Systems is an AI-infrastructure company founded in 2015. It sells rack-scale wafer-scale computing systems and provides cloud-based, API-accessible AI inference alongside on-premises deployments.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build and operate scalable, low-latency inference services. You will deploy Kubernetes workloads, optimize autoscaling and resource allocation, develop Python scripts and APIs, investigate production defects, improve reliability, document systems, and contribute to release planning.
Requirements
- Master's degree in Computer Science or a related field
- One year of relevant software-development experience
- Docker and Kubernetes knowledge
- Java or C++ knowledge
- ActiveMQ and Kafka knowledge
- Python or Groovy knowledge
- JavaScript or TypeScript knowledge
- Linux knowledge
- SQL, OracleDB, and Redis knowledge
- Git knowledge
Responsibilities
- Implement infrastructure for high-performance, low-latency inference services
- Deploy and configure Kubernetes services
- Optimize resource allocation and autoscaling policies
- Integrate inference services with Docker and Kubernetes
- Implement multi-region deployments and disaster recovery strategies
- Develop Python scripts and APIs for inference workflows
- Validate inference accuracy and performance
- Triage and resolve service defects using logs, metrics, and traces
- Debug model deployment, orchestration, and networking issues
- Develop automated failure-detection and mitigation scripts
- Write technical documentation for infrastructure and APIs
- Track defects, enhancements, and release notes in Jira and Git
- Participate in release planning and prioritization