Senior MLOps Engineer

Title: Senior MLOps Engineer (Remote) | Sovereign AILocation: RemoteAbout the role:We are hiring a Senior MLOps Engineer for one of the leading players in Sovereign AI, a UAE-based company with frontier-model access and agentic AI products live across critical sectors at unprecedented scale.You'll own the infrastructure that trains, serves, and scales large language models in production, the systems that keep high-stakes AI running reliably and cost-effectively.What you'll do:Deploy and scale self-hosted open-weight models (from ~7B up to ~370B+ parameters) using engines like vLLM, Triton, or TGI, choosing serving strategies (continuous batching, tensor/pipeline parallelism, quantization) to hit latency and cost targetsOperate a multi-provider gateway spanning self-hosted models and external APIs, with token accounting, budget controls, and cost-aware routingBuild and maintain pipelines for fine-tuning, evaluation, versioning, and continuous delivery (MLflow, SageMaker, or Kubeflow), including distributed training (DeepSpeed, FSDP, Accelerate)Own production reliability: monitoring, logging, alerting, incident response, and safe rollbackWhat we're looking for:5+ years in MLOps, ML infrastructure, or ML engineering, owning end-to-end model lifecycles in productionHands-on experience serving large models at scale (vLLM/Triton/TGI, quantization, GPU optimization)Strong Kubernetes, Docker, and IaC (Terraform)You've been on-call for ML services and handled real incidents, not just built happy-path pipelinesThe setup:Fully remote, contract-basedOnboarding ASAPWorld-class environment: elite talent from FAANG and frontier AI labsInterested? Apply here or message me directly with your CV.