Senior Staff Engineer, Scalable AI Inference & Resilience

Cerebras Systems; United States; Remote; USD 180,000 - 250,000; Full time

Job summary

Cerebras Systems seeks a Sr. Member of Technical Staff to design and develop software features that improve resiliency and availability across distributed environments.

You will help build scalable AI inference services, craft cloud deployment workflows on AWS, and automate reliability through code and testing. You will collaborate with engineering teams to deliver high-performance software, implement Docker/Kubernetes deployments, and contribute to comprehensive monitoring and logging

Qualifications

• Master’s degree or foreign equivalent degree 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.
• Infrastructure-as-Code and deployment automation: Terraform, AWS CloudFormation, AWS CDK, and Ansible.
• Containerization and orchestration: Docker, Kubernetes, AWS EKS, AWS ECS, AWS Fargate, and Helm.
• Compute and serverless services: AWS EC2, AWS Lambda functions, and Auto Scaling Groups.
• Monitoring, logging, and distributed tracing: AWS CloudWatch, AWS X-Ray, ELK, Prometheus, and Grafana.
• Programming languages and frameworks: Python, Node.js, JavaScript, and Flask.
• Data storage and caching: PostgreSQL, Redis, and NFS.
• CI/CD and version control: Jenkins and Git.

Responsibilities

• Design and develop features for resiliency and high availability across distributed environments.
• Develop and maintain cloud-based deployment workflows for AI inference software using AWS for low latency and scalability.
• Develop Python scripts and APIs to streamline data preprocessing, inference, and post-processing for real-time tasks.
• Use parallel programming (multi-threading, async) to maximize resource use on AWS compute.
• Develop components to visualize and analyze system performance metrics (monitoring UI).
• Develop inference software in Docker and define Kubernetes orchestration strategies for reliability and scaling.
• Create automated scripts to detect and mitigate common failure modes to improve reliability.
• Debug issues related to model deployment, containers, networking; document steps and root causes.
• Triage and resolve defects by analyzing logs, metrics, and traces using AWS CloudWatch, Grafana, etc.
• Collaborate with Product and UX to define requirements for inference service interfaces (config, monitoring, logging).
• Document infrastructure configurations, inference workflows, and APIs for internal and external customers.
• Track defects, enhancements, and release notes using Jira and Git.

Skills

Terraform

AWS CloudFormation

Kubernetes

Docker

Python

Node.js

JavaScript

Flask

PostgreSQL

Redis

Jenkins

Git

Grafana

Prometheus

ELK

Education

Master’s degree in Computer Science or related field

Tools

Grafana

Prometheus

ELK Stack

Jenkins

Git

Job description

Cerebras Systems seeks a Sr. Member of Technical Staff to design and develop software features that improve resiliency and availability across distributed environments.

You will help build scalable AI inference services, craft cloud deployment workflows on AWS, and automate reliability through code and testing. You will collaborate with engineering teams to deliver high-performance software, implement Docker/Kubernetes deployments, and contribute to comprehensive monitoring and logging