ML Ops Engineer

ML Ops Engineer (On-Premise) –
Overview

A leading bank in Saudi Arabia is seeking an experienced ML Ops Engineer to support the deployment, scaling, and maintenance of machine learning models within a fully on-premise infrastructure environment. This role focuses on operationalising models post-development, ensuring reliability, traceability, and performance across GPU-based systems.

Key Responsibilities

Deploy, configure, and manage machine learning models on GPU-based infrastructure

Own the end-to-end model lifecycle post-development (deployment → monitoring → maintenance)

Integrate models with vector databases and internal systems

Ensure model traceability, versioning, and auditability (critical for regulated environments)

Monitor model performance and implement improvements where needed

Troubleshoot and optimise GPU performance and resource utilisation

Collaborate with Data Science and Engineering teams to productionise models

Maintain robust documentation and governance aligned with banking standards

Required Skills & Experience

~5+ years of experience in ML Ops / Machine Learning Engineering

Strong experience deploying models on GPU infrastructure (on-premise)

Hands-on experience with:

Model deployment frameworks (e.g. Docker, Kubernetes)

Model versioning and lifecycle tools

Vector databases (e.g. Pinecone, FAISS, Milvus or similar)

Solid understanding of model monitoring, maintenance, and optimisation

Experience working in Linux-based environments