Senior MLOps Platform Engineer — Enterprise

cander; Abu Dhabi; On-site; AED 300,000 - 600,000; Full time

Job summary

AI71, headquartered in Abu Dhabi, seeks a Senior MLOps Engineer to design and implement the core infrastructure for an enterprise AI platform. You will own model serving, CI/CD, and observability across real-time and batch workloads, partnering with data scientists to move from notebooks to scalable production systems.

You will shape standards, tooling, and security controls for mission-critical deployments, balancing rapid delivery with reliability in regulated environments.

Qualifications

• Substantial hands-on experience running machine learning systems in production, with a focus on platform infrastructure rather than model development.
• Deep expertise in Kubernetes and containerization and ownership of cluster-level decisions.
• Proven experience with infrastructure as code (Terraform or equivalent) and end-to-end CI/CD ownership for production systems.
• Familiarity with model serving frameworks such as KServe, Seldon, BentoML, vLLM, or Triton for enterprise deployments.
• Strong software engineering skills in Python, with production-grade code practices.
• Hands-on experience with ML lifecycle tooling and pipeline orchestration (MLflow, Kubeflow, Airflow).
• Experience implementing monitoring and observability for ML systems (Prometheus, Grafana).
• In-depth knowledge of cloud platforms and scalable, secure architectures for enterprises.
• Collaborative mindset to work with data scientists and ML engineers on production-ready deployments.

Responsibilities

• Design and build the model serving layer, including real-time inference and batch processing.
• Develop and implement CI/CD pipelines for models with versioning and rollout controls.
• Establish and maintain a comprehensive observability layer for ML workloads.
• Own evaluation infrastructure and robust validation for production models.
• Build infrastructure as code across environments with strong security and compliance.
• Collaborate with data scientists to streamline notebook-to-production transitions.
• Define architectural standards and internal tooling to optimize deployment and operations.

Skills

Kubernetes

Infrastructure as Code

Model serving

Python production

ML lifecycle tooling

Observability

Cloud platforms

Production ML systems

Data science collaboration

Tools

KServe

Seldon

BentoML

vLLM

Triton

Job description

AI71, headquartered in Abu Dhabi, seeks a Senior MLOps Engineer to design and implement the core infrastructure for an enterprise AI platform. You will own model serving, CI/CD, and observability across real-time and batch workloads, partnering with data scientists to move from notebooks to scalable production systems.

You will shape standards, tooling, and security controls for mission-critical deployments, balancing rapid delivery with reliability in regulated environments.