Agent Runtime Platform Engineer | IDC Technologies | Abu Dhabi

IDC Technologies, Inc.; Abu Dhabi; On-site; AED 350,000 - 550,000; Full time

Job summary

IDC Technologies, Inc. seeks a seasoned Agent Runtime Platform Engineer in Abu Dhabi to design, deploy, and scale enterprise AI agent platforms. You will lead AKS clusters, Terraform-based automation, and CI/CD pipelines while upholding strict security and availability requirements.

You will collaborate with AI research, data engineering, and software teams to optimize performance and resource allocation, bridging traditional DevOps with advanced AI runtimes.

Qualifications

• 8+ years of cloud/platform engineering or DevOps/SRE experience.
• Experience with Microsoft Azure, AKS, and containerization (Docker/Kubernetes).
• Terraform IaC experience for automated deployments.
• Proven CI/CD pipeline automation and software delivery lifecycle management.
• Strong cloud networking, security hardening, and IAM knowledge.
• Experience with AI agents, MCP, or LLM runtime environments is a plus.
• Bachelor’s degree in CS/IT/SE or related field.
• Excellent analytical and cross-functional communication skills.

Responsibilities

• Design, deploy, and scale platform and cloud architectures for AI workloads.
• Administer and optimize Azure AKS clusters and containers.
• Implement IaC automation using Terraform for rapid deployments.
• Build, maintain, and secure CI/CD pipelines for software delivery.
• Configure cloud networking and zero-trust security policies.
• Deploy runtime environments for AI Agents and MCP in production.
• Collaborate with data science and software teams to optimize performance and resources.
• Ensure high availability and disaster recovery with strict security standards.

Skills

Cloud engineering

DevOps practices

SRE mindset

Cross-functional collaboration

Education

Bachelor’s degree in Computer Science/IT/Software Engineering

Tools

Terraform

Docker

Kubernetes

Azure AKS

Job description

Position Summary

IDC Technologies is seeking a seasoned and hands-on Agent Runtime Platform Engineer to join our technology team in Abu Dhabi. In this critical senior role, you will be responsible for designing, deploying, and scaling advanced cloud infrastructure and platform architectures tailored for artificial intelligence and autonomous AI agent workflows. You will lead container orchestration strategies, manage multi-cloud Kubernetes environments, and ensure high availability, robust security, and optimal performance for next-generation AI applications. This opportunity requires an experienced platform or cloud engineer with 8+ years of professional expertise who can bridge traditional DevOps principles with cutting-edge AI agent runtime systems.

Detailed Job Description

As the Agent Runtime Platform Engineer, you will take full ownership of building and maintaining the foundational infrastructure that powers enterprise AI agents and model control protocols (MCP). Your day-to-day responsibilities include provisioning and optimizing Azure Kubernetes Service (AKS) clusters, managing containerized workloads, automating infrastructure provisioning via Terraform, and enforcing rigorous security and networking guardrails. You will collaborate closely with AI research, data engineering, and software development teams to streamline CI/CD deployment pipelines, monitor run-time latency, and scale distributed AI agent architectures efficiently across enterprise environments. Furthermore, you will establish operational best practices, troubleshoot complex cloud infrastructure bottlenecks, and ensure strict compliance with enterprise security standards.

Key Responsibilities

• Design, deploy, and scale robust platform and cloud architectures supporting enterprise AI agents and generative AI workloads.
• Administer and optimize Azure cloud environments and Azure Kubernetes Service (AKS) container clusters.
• Implement and manage infrastructure-as-code automation frameworks using Terraform for rapid, repeatable deployments.
• Build, maintain, and secure automated CI/CD pipelines for continuous integration and seamless software delivery.
• Configure and troubleshoot complex cloud networking, microservices communication, and zero-trust security policies.
• Deploy and manage runtime environments for AI Agents and Model Control Protocols (MCP) in production settings.
• Collaborate with cross-functional data science and software engineering teams to optimize agent performance and resource allocation.
• Ensure high system availability, disaster recovery readiness, and rigorous adherence to enterprise security protocols.

Required Qualifications & Skills

• Minimum of 8 years of professional experience in cloud engineering, platform engineering, DevOps, or site reliability engineering.
• Extensive hands‑on experience working with Microsoft Azure, Azure Kubernetes Service (AKS), and containerization technologies (Docker, Kubernetes).
• Demonstrated expertise in infrastructure‑as‑code (IaC) toolsets, specifically Terraform.
• Strong proficiency in building automated CI/CD pipelines and managing software delivery lifecycles.
• Solid understanding of cloud networking architectures, security hardening, and identity access management.
• Practical exposure to AI agents, LLM runtime environments, or Model Control Protocols (MCP).
• Bachelor’s degree in Computer Science, Information Technology, Software Engineering, or a related technical discipline.
• Excellent analytical, problem-solving, and cross‑functional communication skills.

Nice-to-Have Skills

• Professional certifications such as Microsoft Certified: Azure DevOps Engineer Expert or Certified Kubernetes Administrator (CKA).
• Prior experience integrating vector databases, embedding pipelines, or LLM serving frameworks (e.g., vLLM, TGI).
• Advanced scripting skills in Python, Go, or Bash for platform automation and custom tool development.
• Previous experience operating within fast‑paced IT consultancy or global technology staffing environments in the GCC region.
• Strong familiarity with observability and monitoring platforms such as Prometheus, Grafana, and Datadog.

Salary and Contract Information

Salary/Rate: Market Competitive / Industry Standard

Deadline: Open until filled

Notice Period: Immediate to 15 Days

Contract Duration: Permanent / Full-Time