Job Description

Location: Abu Dhabi, UAE
Experience: 7+ Years

Role Overview:

We are seeking for Agent Runtime Platform Engineer to design and build the enterprise runtime foundation for AI agents and agentic applications. The role is focused on platform engineering, with a strong understanding of agent engineering standards and deployment patterns.

The engineer will create secure, reusable, and self-service runtime capabilities that enable teams to deploy agents consistently across cloud-native environments.

Key Responsibilities:

Agent Runtime & Platform Engineering

Design and engineer runtime patterns for AI agents, MCP servers, APIs, and containerized services.
Build runtime capabilities using AKS, Azure Container Apps, Kubernetes, queues, events, and cloud-native infrastructure.
Build reusable infrastructure patterns and platform APIs for consistent deployment and operation of agent workloads.
Define standards for agent manifests, runtime configurations, and tool definitions.

Integration & Security

Standardize how agents connect to models, MCP servers, and enterprise APIs.
Implement approved patterns for networking, identity, and access control.
Develop paved-road templates, SDKs, reference implementations, documentation, and onboarding journeys for application teams.

Production Readiness

Ensure agent workloads are observable, scalable, secure, and production-ready.
Apply appropriate practices for resilience, cost control, release promotion, and operational readiness.

Required Skills & Experience:

7+ years of relevant experience.
Strong hands-on expertise with:
- AKS
- Azure Container Apps
- Kubernetes
- Containers
- Networking
- Workload Identity
- Ingress
- API Gateways
- Private Connectivity
- Secrets Management
Strong experience with Terraform and GitHub Actions or equivalent automation.
Experience developing reusable platform modules, deployment templates, and environment-aware provisioning.
Working knowledge of AI agent architectures and API/service contracts.
Strong understanding of security, observability, scaling, resilience, cost control, release promotion, and operational readiness.
Ability to work closely with AI Platform, AI Ops, Cybersecurity, Architecture, and Application teams.