GenAI Deployment Engineer for Enterprise On‑Prem

Zohorecruit; Riyadh; On-site; SAR 240,000 - 360,000; Full time

Job summary

Tangram.ai seeks a Forward Deployed AI Engineer in Riyadh, Saudi Arabia to deploy and operationalize enterprise GenAI platforms within secure, on-premise and air-gapped banking environments.

You will work with client IT, infrastructure, security and AI teams to translate platform architectures into production deployments and optimize AI workloads for reliability in regulated settings.

Qualifications

• 4+ years in Software Engineering, DevOps, Platform Engineering or related field.

Responsibilities

• Deploy and configure NVIDIA NIMs, LLMs, DataRobot, Graph Databases.
• Install and manage AI workloads on OpenShift and Kubernetes environments.
• Package and deploy container images, dependencies, and LLM weights in air-gapped environments.
• Configure NVIDIA GPU Operator, GPU time-slicing and MIG for AI workloads.
• Optimize LLM inference performance: throughput, latency and GPU utilization.
• Build CI/CD and GitOps pipelines using ArgoCD and OpenShift Pipelines.
• Develop and maintain Helm charts, Kustomize manifests and Kubernetes configurations.
• Troubleshoot deployment, infrastructure, networking and performance issues in secure client environments.
• Work directly with client IT, Security and Infrastructure teams to resolve blockers.

Skills

OpenShift

Kubernetes

NVIDIA GPUs

LLM Deployment

MLOps / LLMOps

Docker / OCI

GitOps

ArgoCD

DataRobot

Triton Inference Server

Graph Databases

Education

CKA / CKAD certification

Tools

OpenShift Pipelines

Helm

Kustomize

Kubectl

Job description

Tangram.ai seeks a Forward Deployed AI Engineer in Riyadh, Saudi Arabia to deploy and operationalize enterprise GenAI platforms within secure, on-premise and air-gapped banking environments.

You will work with client IT, infrastructure, security and AI teams to translate platform architectures into production deployments and optimize AI workloads for reliability in regulated settings.