Senior MLOps Engineer: Scale LLMs & Speech Inference

Institute of Foundation Models; Abu Dhabi; On-site; AED 260,000 - 450,000; Full time

Job summary

Institute of Foundation Models invites a Senior MLOps Engineer to design, build, and maintain robust ML infrastructure across training, inference, and deployment pipelines. You will own the model lifecycle from data ingestion to real-time serving in Kubernetes-based environments.

Join a cross-disciplinary team of researchers and engineers, work with vLLM, ElevenLabs, Whisper, and OpenWebUI, and help scale cloud deployments with Terraform, Helm, and AWS.

Qualifications

• 4+ years of experience in MLOps, DevOps, or Cloud Infrastructure Engineering for ML systems.

Responsibilities

• Design and manage scalable ML infrastructure on AWS using EKS, EC2, RDS, S3, and IAM.
• Build Kubernetes deployments for LLM and TTS inference with Helm, ArgoCD, and monitoring.
• Implement and optimize model serving pipelines with vLLM, SGLang, TensorRT, or Ray Serve.
• Develop CI/CD and MLOps automation for data versioning, model validation, deployment.
• Integrate OpenWebUI, Gradio, or similar UIs for demos and evaluation tools.

Skills

Kubernetes

CI/CD

Python

Cloud infrastructure

Observability

Tools

AWS

Terraform

Docker

Prometheus

Grafana

ArgoCD

OpenWebUI

Gradio

TensorRT

Job description

Institute of Foundation Models invites a Senior MLOps Engineer to design, build, and maintain robust ML infrastructure across training, inference, and deployment pipelines. You will own the model lifecycle from data ingestion to real-time serving in Kubernetes-based environments.

Join a cross-disciplinary team of researchers and engineers, work with vLLM, ElevenLabs, Whisper, and OpenWebUI, and help scale cloud deployments with Terraform, Helm, and AWS.