Senior LLMOps / AI Platform Engineer

Hire Rightt; Dubai; On-site; AED 180,000 - 240,000; Full time

Job summary

Hire Rightt seeks an AI Infrastructure Engineer to design, deploy, and optimize production-grade LLM and Generative AI infrastructure. You will work on LLM inference, GPU optimization, Kubernetes orchestration, and cloud-based AI services.

The role covers observability, state management, and scalable AI workflows. You will deploy self-hosted LLMs, optimize performance across GPUs, and build CI/CD pipelines for AI services, while ensuring reliability and cost efficiency in a fast-paced

Qualifications

• Proficiency in Python and FastAPI for building production-grade AI services.
• Experience deploying self-hosted LLMs (vLLM, Hugging Face) and managing GPU inference.
• Strong knowledge of Kubernetes, Docker, Helm and AWS.
• Experience with LLM observability and monitoring.
• Familiarity with RAG, embeddings, and vector databases (Qdrant/Milvus).
• Experience with LangChain/LangGraph/LangSmith for AI workflows.

Responsibilities

• Deploy and operate self-hosted LLMs using vLLM, SGLang, Ollama.
• Optimize LLM inference for latency, throughput, concurrency, GPU memory, KV cache and cost.
• Manage GPU workloads across multiple NVIDIA GPUs.
• Deploy and maintain AI services on Kubernetes / AWS EKS using Docker and Helm.
• Implement LLM reliability with health checks, monitoring, and automated recovery strategies.
• Set up observability using OpenTelemetry, Prometheus, Grafana, Langfuse/LangSmith.
• Develop and optimize RAG systems, embeddings and vector databases (Qdrant, Milvus).
• Support AI agents and workflows built with LangChain and LangGraph.

Skills

Python

FastAPI

Kubernetes

Docker

GPU optimization

LangChain

LangGraph

LangSmith

RAG

embeddings

PostgreSQL

Redis

Tools

vLLM

Ollama

Hugging Face

Kubernetes

Docker

Helm

AWS

Qdrant

Milvus

LangChain

Job description

Location:

Dubai

Role Overview:

The job holder will be responsible for building, deploying, optimizing, and operating production-grade LLM and Generative AI infrastructure. The role combines LLM inference, GPU optimization, Kubernetes, cloud infrastructure, observability, RAG, and AI platform engineering.

Responsibilities:

• Deploy and operate self-hosted LLMs using vLLM, SGLang, Ollama.
• Optimize LLM inference for latency, throughput, concurrency, GPU memory, KV cache, and cost.
• Manage GPU workloads across multiple NVIDIA GPUs.
• Deploy and maintain AI services on Kubernetes / AWS EKS using Docker and Helm.
• Implement LLM reliability mechanisms including health checks, monitoring, automated recovery, and model restart/refresh strategies.
• Implement observability using Langfuse/LangSmith, OpenTelemetry, Prometheus, and Grafana.
• Deploy and optimize RAG systems, embedding models, and vector databases such as Qdrant, Milvus.
• Support AI agents and workflows built with LangChain and LangGraph.
• Build and maintain CI/CD pipelines for AI services and infrastructure.
• Troubleshoot production issues across LLMs, GPUs, Kubernetes, networking, and AI applications.

Requirements:

• Strong Python and FastAPI experience
• vLLM, Hugging Face and self-hosted LLM deployment
• Kubernetes, Docker, Helm and AWS
• NVIDIA GPU inference and performance optimization
• LangChain / LangGraph/LangSmith
• RAG, embeddings and vector databases (Qdrant)
• LLM observability and monitoring
• PostgreSQL / Redis GitHub Actions / CI/CD
• Strong production troubleshooting skills