Remote
Job Description
Our client is seeking a talented and self-motivated Senior DevOps to support Azure OpenAI. You'll play a crucial role in designing, implementing, and maintaining the infrastructure and deployment processes for AI models. Your focus will be on ensuring seamless integration, continuous delivery, and efficient management of OpenAI services within an Azure environment. You will be assisting in developing our core team and helping to deliver a highly available platform for software solutions while collaborating with their larger Technology team globally. This is an exciting opportunity to play a leading role in changing the way that our client's products are delivered within the company and to their customers, devising and implementing a modern approach to infrastructure engineering that enables continuous delivery and releases features on-demand.
The role holder will have excellent technical and project management skills as you'll be part of the Technology Infrastructure and Operations (TIO) team supporting, designing, migrating, and implementing products globally deployed within the Microsoft Azure Cloud
Qualifications
- 5+ years of Systems Engineering experience
- BS Engineering/Computer Science or equivalent experience required
Key Tasks
- Collaborate with software engineers, testers, and system administrators to ensure smooth integration of OpenAI services into applications. Foster a culture of teamwork and continuous improvement
- Set up monitoring, logging, and alerting for OpenAI services. Optimize resource utilization, scalability, and performance
- Develop and maintain infrastructure patterns supporting the promotion and deprecation of OpenAI and other LLM models within an API configuration
- Building and maintaining a set of tools that enable automation for creating and supporting Azure subscriptions in a large-scale tenant
- Improving existing Continuous integration across multiple product pipelines
- Oversee the day-to-day remediation of critical issues and building processes and efficiencies to eliminate the recurrence of the issue
- Maintain the health and security of infrastructure by monitoring and patching
- Ability to deliver TIO strategy in partnership with the business platform needs
- Participate in off-hours on-call support schedule
Key Skills / Experience
- 3 - 5 years of experience with administering Microsoft Azure subscriptions in an Enterprise environment
- Understand Azure deployment processes such as Azure Blueprints, ARM templates, and PowerShell Modules
- Proficiency with the Azure Command Line (CLI) interface
- Deep knowledge of Azure Active Directory, IAM, and Roles
- Practiced in Azure infrastructure - Virtual Machines, Azure Storage, Azure App Service and Database offerings
- Understand Azure VNETS, Express route, Internet networking, Virtual Private Networks and DNS
- Familiarity with Azure Cognitive Services and its component offerings
- Ability to use Terraform in an enterprise environment, including module creation and use
- Advanced Linux and Windows server administration experience
- Docker and Containerization, Kubernetes a plus
- Git and source control procedures
- An understanding of coding practices and DRY principles
- Authoring scripts with Bash and Python
- Executing and tracking tasks in an Agile environment
- Continuous Integration systems such as Jenkins and GitHub Actions
- Ability to work on several work streams with excellent time management
- Able to formulate and execute solutions to take into consideration the needs of multiple stakeholders
- A positive, constructive approach with an emphasis on collaboration and good execution
- Able to mentor and lead other members of the team
TOP 3 must-have skills:
- Experience with Microsoft Azure in an Enterprise setting. Support for multiple subscriptions and tenants
- Terraform
- Familiarity of OpenAI or other Large Language Model (LLM) systems
Certifications:
AZ-104 - Azure Administrator Associate (Strong preference)
AI-900 - Azure AI Fundamentals (Nice to have)
AI-102 - Designing and Implementing a Microsoft Azure AI Solution (Nice to have)
“All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or status as a protected veteran”
