AI/ML Engineer

We are seeking an experienced Al/ML Engineer with strong expertise in deploying and maintaining machine-learning services at scale. The ideal candidate will be responsible for running and enhancing our GPU-powered Al infrastructure, ensuring high performance as user demand grows, and integrating new models and pipelines.
This is an urgent requirement — candidates must be ready to join within 15 days.

Responsibilities
•Deploy, monitor and maintain production AI/ML services on GPU servers (RunPod).
•Scale GPU infrastructure and load-balancing to meet growing user demand; implement autoscaling and cost controls.
•Optimize inference speed and reliability through batching, quantization, caching and other performance techniques.
•Integrate AI models into existing services as required.
•Enhance our current AI model.
•Build and maintain asynchronous processing and queue systems (Celery/Redis or equivalent).
•Implement safety filters and other guardrails around model outputs.
•Ensure zero-touch operations: automatic startup, model pre-loading, health checks, alerts and automated restarts.
•Expose clean API endpoints and work closely with backend developer for seamless integration with the main application.
•Maintain dashboards for GPU usage, latency, error rates and alerting.
•Document all infrastructure, deployment processes and enhancements clearly for handover and future scaling.

Requirements:

Salary:
OMR 400 to 500 per month inclusive of fixed allowances.