MLOps Engineer for Scalable GPU LLM Deployments

First.tech Group; Abu Dhabi Emirate; On-site; AED 300,000 - 540,000; Full time

Benefits offered by this job

Health & wellness support

Career development

Performance-based incentives

Job summary

First Tech is seeking an experienced MLOps Engineer to build and operate the infrastructure powering our LLM applications in production. You will work on GPU-backed inference, secure deployment pipelines, and multi-cloud infrastructure.

You will design scalable CI/CD for containerized services, implement retrieval and caching layers, and ensure security/compliance across data and pipelines while collaborating with cross-functional teams in Abu Dhabi.

Qualifications

• 3+ years in MLOps, LLMOps, DevOps, or infrastructure/platform engineering.
• Container orchestration with GPU scheduling, autoscaling and security policies.
• Multi-cloud experience across AWS, GCP or Azure.
• IaC for multi-environment deployments (e.g., Terraform).
• Cloud security fundamentals: IAM, VPC, encryption, audit logs.
• Observability: logging, monitoring, tracing, SLO management.
• LLM inference serving frameworks (e.g., vLLM, Triton).
• Inference optimization (quantization, batching, KV-cache).
• Familiar with security/compliance in regulated industries.

Responsibilities

• Deploy, scale, and maintain GPU-backed LLM workloads on Kubernetes.
• Architect and provision multi-cloud infrastructure using IaC.
• Optimize LLM inference for latency, throughput, and cost.
• Build and maintain CI/CD pipelines for containerized services.
• Design retrieval and caching layers for production LLM apps.
• Monitor system health and lead incident response for model endpoints.
• Maintain evaluation pipelines to catch quality regressions.
• Enforce security and compliance across infra and data pipelines.

Skills

MLOps

Kubernetes

Multi-cloud

Terraform

Observability

Security basics

LangSmith

vLLM

Triton

Tools

Terraform

LangSmith

vLLM

Triton

Kubernetes

Job description

First Tech is seeking an experienced MLOps Engineer to build and operate the infrastructure powering our LLM applications in production. You will work on GPU-backed inference, secure deployment pipelines, and multi-cloud infrastructure.

You will design scalable CI/CD for containerized services, implement retrieval and caching layers, and ensure security/compliance across data and pipelines while collaborating with cross-functional teams in Abu Dhabi.