MLOps/LLMOps Engineer

datascience; Riyadh; On-site; SAR 260,000 - 380,000; Full time

Job summary

datascience is seeking an experienced ML engineer to build and manage MLOps and LLMOps pipelines in a Saudi Arabian environment. You will automate deployment workflows, monitor performance drift, and oversee model serving frameworks like vLLM, TGI, and Ray Serve.

The role emphasizes experiment tracking, versioning, governance, and reproducibility across end-to-end ML pipelines with a focus on compliance and scalable deployment.

Qualifications

• 4+ years of experience in ML/AI pipelines or related fields.
• Experience building and managing MLOps/LLMOps stacks.
• Strong knowledge of model versioning and governance practices.

Responsibilities

• Build and manage MLOps and LLMOps pipelines.
• Automate model deployment using CI/CD pipelines.
• Monitor model performance drift and retraining cycles.
• Manage model serving frameworks such as vLLM, TGI, Ray Serve.
• Implement experiment tracking and model versioning.
• Ensure governance, reproducibility, and compliance.

Skills

ML workflows

LLM serving

Experiment tracking

Model versioning

Governance & compliance

Tools

Kubernetes

Docker

GitLab

Jenkins

Azure DevOps

CI/CD tools

Job description

Responsibilities

• Build and manage MLOps and LLMOps pipelines
• Automate model deployment using CI/CD pipelines
• Monitor model performance drift and retraining cycles
• Manage model serving frameworks such as vLLM, TGI, Ray Serve
• Implement experiment tracking and model versioning
• Ensure governance, reproducibility, and compliance

Requirements

• Minimum 4 years of experience in relevant fields
• Experience with Kubernetes, Docker, and CI/CD tools (GitLab, Jenkins, Azure DevOps)
• Proficiency with ML frameworks (TensorFlow, PyTorch)
• Knowledge of LLM serving and optimization