Senior DevOps Engineer - AI & Agentic Systems

GSSTech Group; Dubai; On-site; AED 120,000 - 200,000; Full time

Job summary

A leading tech company in Dubai is seeking a highly skilled Senior DevOps Engineer. You will be responsible for architecting AI-driven systems, integrating AI models, and managing cloud infrastructure to ensure high availability and performance. The ideal candidate will have over 5 years of experience in DevOps and strong skills in Docker and Kubernetes. Join us to contribute to cutting-edge AI solutions in a fast-paced environment.

Qualifications

• 5+ years of experience in DevOps or cloud infrastructure engineering.
• Strong hands-on experience with Docker, Kubernetes, and CI/CD pipelines.
• Experience with LLMs, AI model deployment, or MLOps workflows is a strong plus.

Responsibilities

• Design and implement modular architectures that integrate LLMs.
• Evaluate, select, and integrate suitable AI models into production environments.
• Build and deploy intelligent agents for research and task automation.
• Manage containerized environments ensuring high availability and performance.
• Establish content filtering and data protection mechanisms.
• Collaborate with cross-functional teams for technical AI solutions.
• Monitor agent performance and optimize system behavior.

Skills

Docker

Kubernetes

CI/CD pipelines

Problem-solving skills

Python-based AI frameworks

Education

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

Tools

AWS

Azure

GCP

Terraform

Ansible

Job description

We are seeking a highly skilled Senior DevOps Engineer with experience in architecting and deploying Agentic AI systems. The ideal candidate will have a strong background in DevOps, cloud infrastructure, and modern AI integrations, including LLM-based systems and autonomous agent development.

Key Responsibilities:

• Architect AI-Driven Systems: Design and implement modular architectures that integrate large language models (LLMs) and support multi-step reasoning, retrieval-augmented generation (RAG), and external tool usage.
• AI Model Integration: Evaluate, select, and integrate suitable AI models (e.g., GPT-5, custom LLMs) into scalable production environments.
• Agent Development: Build and deploy intelligent agents capable of research, summarization, task automation, and action execution.
• Infrastructure & Scalability: Manage containerized environments using Docker and Kubernetes, ensuring high availability, performance, and security.
• Responsible AI Practices: Establish and maintain content filtering, audit logging, and data protection mechanisms to ensure ethical AI operations.
• Stakeholder Collaboration: Work closely with cross-functional teams to translate business needs into scalable technical AI solutions.
• Continuous Optimization: Monitor agent performance, analyze errors, refine prompts, and optimize system behavior for accuracy and efficiency.

Requirements:

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
• 5+ years of experience in DevOps or cloud infrastructure engineering.
• Strong hands‑on experience with Docker, Kubernetes, and CI/CD pipelines.
• Experience with LLMs, AI model deployment, or MLOps workflows is a strong plus.
• Knowledge of cloud platforms (AWS, Azure, or GCP) and infrastructure as code (Terraform, Ansible, etc.).
• Excellent problem‑solving skills and the ability to work in a fast‑paced, AI‑focused environment.

Preferred Skills:

• Experience with Python‑based AI frameworks and APIs.
• Familiarity with retrieval systems, vector databases, or RAG pipelines.
• Understanding of data governance, compliance, and responsible AI principles.