Senior LLMOps / AI Platform Engineer

IC; Dubai; On-site; AED 480,000 - 640,000; Full time

Job summary

IC Markets Global seeks a Senior LLMOps/AIPlatformEngineer to build, deploy, optimize, and operate production-grade LLMs and Generative AI infrastructure.

The role blends LLM inference, GPU optimization, Kubernetes, cloud infrastructure, observability, RAG, and AI platform engineering to enable scalable AI services and AI agents at scale.

Qualifications

• Proficient in Python programming and FastAPI for building AI services.
• Experience deploying and self-hosting LLMs (vLLM, HuggingFace) and managing GPU workloads.
• Strong knowledge of Kubernetes, Docker, Helm, and cloud platforms (AWS).
• Familiar with LangChain/LangGraph/LangSmith and RAG technologies.
• Understanding of observability stacks (OpenTelemetry, Prometheus, Grafana) and CI/CD pipelines.

Responsibilities

• Deploy and operate self-hosted LLMs using vLLM, SGLang, Ollama.
• Optimize LLM inference for latency, throughput, and cost.
• Manage GPU workloads across multiple NVIDIA GPUs.
• Deploy and maintain AI services on Kubernetes/AWS EKS with Docker and Helm.
• Implement reliability and recovery strategies for LLMs and models.

Skills

Python

FastAPI

vLLM

HuggingFace

Kubernetes

Docker

AWS

NVIDIA GPU

LangChain

LangGraph

LangSmith

RAG

Vector databases

PostgreSQL

Redis

CI/CD

Tools

Kubernetes

Docker

Helm

AWS

LangChain

LangGraph

LangSmith

Prometheus

Grafana

OpenTelemetry

Qdrant

Milvus

GitHub Actions

Job description

ICMarketsGlobalisoneofthemostrenownedForexCFDprovider,offeringtradingsolutionsforactivedaytradersandscalpersaswellastradersthatarenewtotheforexmarket.ICMarketsGlobaloffersitsclientscuttingedgetradingplatforms,lowlatencyconnectivityandsuperiorliquidity.

ICMarketsGlobalisrevolutionizingonlineforextrading.Tradersarenowabletogainaccesstopricingpreviouslyonlyavailabletoinvestmentbanksandhighnetworthindividuals.

OurmanagementteamhavesignificantexperienceintheForex,CFDandEquitymarketsinAsia,EuropeandNorthAmerica.Itisthisexperiencethathasenabledustoselectthebestpossibletechnologysolutionsandhandpicksomeofthebestpricingprovidersavailableinthemarket.

AbouttheRole

WearelookingforaSeniorLLMOps/AIPlatformEngineertobuild,deploy,optimize,andoperateproduction-gradeLLMandGenerativeAIinfrastructure.

TherolecombinesLLMinference,GPUoptimization,Kubernetes,cloudinfrastructure,observability,RAG,andAIplatformengineering.

KeyResponsibilities

• Deployandoperateself-hostedLLMsusingvLLM,SGLang,Ollama.
• OptimizeLLMinferenceforlatency,throughput,concurrency,GPUmemory,KVcache,andcost.
• ManageGPUworkloadsacrossmultipleNVIDIAGPUs.
• DeployandmaintainAIservicesonKubernetes/AWSEKSusingDockerandHelm.
• ImplementLLMreliabilitymechanismsincludinghealthchecks,monitoring,automatedrecovery,andmodelrestart/refreshstrategies.
• ImplementobservabilityusingLangfuse/LangSmith,OpenTelemetry,Prometheus,andGrafana.
• DeployandoptimizeRAGsystems,embeddingmodels,andvectordatabasessuchasQdrant,Milvus.
• SupportAIagentsandworkflowsbuiltwithLangChainandLangGraph.
• BuildandmaintainCI/CDpipelinesforAIservicesandinfrastructure.
• TroubleshootproductionissuesacrossLLMs,GPUs,Kubernetes,networking,andAIapplications.

RequiredSkills

• StrongPythonandFastAPIexperience
• vLLM,HuggingFaceandself-hostedLLMdeployment
• Kubernetes,Docker,HelmandAWS
• NVIDIAGPUinferenceandperformanceoptimization
• LangChain/LangGraph/LangSmith
• RAG,embeddingsandvectordatabases(Qdrant)
• LLMobservabilityandmonitoring
• PostgreSQL/Redis
• GitHubActions/CI/CD
• Strong production troubleshooting skills