Platform Engineer

AI PlatformEngineer

As an AI PlatformEngineer, you are responsible for the design, stability, and continuous evolution of the Global AI Platform and its associated services.
You ensure that the platform provides secure, governed, and reliable access to AI capabilities while meeting the operational, performance, and cost expectations of the business.

You work as part of a global platform team, contributing hands-on to the deployment, operation, and improvement of the AI Platform, collaborating closely with engineering, security, infrastructure, and business stakeholders to enable AI adoption at scale.

Key Responsibilities

• Contribute to the design, implementation, and evolution of the Global AI Platform, ensuring scalability, security, and reliability across environments.

• Operate and maintain core platform components, including Azure AI Foundry, Azure API Management (APIM), AI gateways (e.g., Portkey), and supporting Azure services.

• Monitor platform health, troubleshoot incidents, and resolve operational issues to ensure continuous availability and performance of AI services.

• Manage and fulfill platform-related requests such as onboarding new use cases, enabling models, configuring integrations, and managing access controls.

• Design and implement infrastructure-as-code (IaC) using Terraform to enable consistent, automated, and repeatable platform deployments.

• Develop and maintain CI/CD pipelines using Azure DevOps to support platform configuration, deployment, and lifecycle management.

• Define and implement platform governance, including model access policies, guardrails, usage controls, and integration standards.

• Enable secure exposure and consumption of AI services through Azure APIM and AI gateways, ensuring proper authentication, authorization, and traffic management.

• Collaborate with solution architects, data scientists, and application teams to onboard and support AI use cases aligned with platform standards.

• Identify opportunities to enhance platform capabilities, improve operational efficiency, and evolve the platform in line with business needs and technological advancements.

• Maintain platform documentation, architecture artifacts, and operational procedures to support knowledge sharing and platform sustainability.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.

• 5+ years of experience in platform engineering, cloud engineering, or infrastructure roles, preferably with exposure to AI/ML platforms.

• Strong hands-on experience with Microsoft Azure, including:

• Azure AI Foundry

• Azure API Management (APIM)

• Azure DevOps

• Core Azure networking, identity, and security concepts

• Proven experience operating cloud platforms in production environments, including incident management and troubleshooting.

• Hands-on experience with Infrastructure as Code (Terraform) and multi-environment deployment strategies.

• Experience working with AI gateways or API gateway technologies (e.g., Portkey or similar) for managing and governing AI/LLM access.

• Solid understanding of API management, service integration patterns, and secure exposure of services.

• Familiarity with AI platform concepts such as model lifecycle, LLM access control, and guardrails.

• Strong problem-solving skills and ability to work in distributed, cloud-based environments.

• Experience working in Agile teams and collaborating across multiple stakeholders.

• Good communication skills, with the ability to clearly articulate technical concepts to both technical and non-technical audiences.