Sr. Member of Technical Staff - AI Inference Software

About the role

Cerebras Systems builds the world's largest AI chip, designed to deliver training and inference speeds over 10 times faster than GPU-based cloud services. It is seeking a Sr. Member of Technical Staff to design and develop software features that support system resiliency and high availability across distributed environments, while building and maintaining scalable AI inference services, cloud-based deployment workflows and improving reliability through automation.

Key responsibilities

• Design and develop software features supporting resiliency and high availability, including automated recovery and fault-tolerant architecture.
• Develop and maintain cloud deployment workflows for AI inference software using AWS tools and services.
• Write Python scripts and APIs for data preprocessing, inference execution and post-processing, and use parallel programming to maximize resource efficiency on AWS compute.
• Build components for visualizing and analyzing system performance metrics, and develop inference software in Docker with Kubernetes orchestration.
• Write scripts to detect and mitigate common failure modes, and debug model deployment, container orchestration and networking issues.
• Triage and resolve defects using logs, metrics and distributed traces with tools such as AWS CloudWatch, Grafana or custom Python scripts.
• Work with Product Management and UX teams on inference service interface requirements, and author technical documentation for infrastructure, workflows and APIs.
• Document and track defects, enhancements and release notes using Jira and Git.

Required profile

• Master's degree or foreign equivalent in Computer Science or a related field.
• 18 months of experience as an Information Security Analyst, Software Engineer, Sr. Member of Technical Staff, IT Senior Applications Engineer or a related occupation.

Required skills

• Infrastructure-as-code and deployment automation: Terraform, AWS CloudFormation, AWS CDK, Ansible.
• Containerization and orchestration: Docker, Kubernetes, AWS EKS, ECS, Fargate, Helm.
• AWS compute and serverless: EC2, Lambda, Auto Scaling Groups.
• Monitoring and tracing: CloudWatch, X-Ray, ELK stack, Prometheus, Grafana.
• Programming: Python, Node.js, JavaScript, Flask.
• Data storage and caching: PostgreSQL, Redis, NFS.
• CI/CD and version control: Jenkins, Git.