Company logo hidden

MLOps / Platform Engineer — LLM Serving & Model Routing

Unlock employer Dubai, United Arab Emirates Direct to Company Under an hour ago · 22 Nov 2026

Financial

  • Estimate: $90k - $130k/yr*
  • Zero income tax location

Accessibility

  • Hybrid
  • Visa Provided

Requirements

  • Experience: Senior
  • English: Professional

Position

About the Role
As a key contributor in the field of data, analytics, and AI, you will stand up and run the model-serving platform that supports a production Agentic AI build. This involves leveraging open-source models that are self-hosted on-premise, utilizing vLLM and a LiteLLM router, along with a model garden that spans across private cloud, a regional provider, and a hyperscaler region. Your work will focus on establishing routing driven by cost, performance, and data sensitivity to ensure optimal functionality.

Ready to apply for roles like this?

Unlock the company name and direct application link. Subscribers get instant access to fresh jobs across Dubai, Abu Dhabi and Riyadh, many with visa support.

Unlock employer & apply directly

What You Will Do

  • Deploy and operate self-hosted open-source models on vLLM using on-premise GPU infrastructure.
  • Build and run the LiteLLM routing layer and maintain the model-garden register of approved models, along with data handling.
  • Size and tune GPU serving by managing quantization, KV-cache, and concurrency planning to maintain the on-premise footprint under load.
  • Implement multi-environment inference across private cloud, a regional provider, and AWS Bedrock or Azure AI Foundry, ensuring routing rules comply with data residency requirements.
  • Oversee observability, fallback options, cost management, and performance metrics of the serving layer.

What You Bring

  • Proven experience in MLOps or ML platform engineering, particularly with direct LLM serving (vLLM, TGI or equivalent).
  • Experience with a model gateway or router in a production setting (e.g., LiteLLM or similar).
  • In-depth knowledge of GPU infrastructure, including CUDA, VRAM and KV-cache sizing, along with an understanding of quantization trade-offs and concurrency issues.
  • Familiarity with Kubernetes and containers, CI/CD practices, and cloud services (AWS and/or Azure), as well as capabilities in monitoring and cost control.

Nice to Have

  • Experience with open-weight models such as Qwen, GPT-OSS, and Kimi.
  • Knowledge of sovereign or data-residency-constrained deployments; familiar with Terraform or other infrastructure as code tools; experience in telecom scale environments.

Benefits

  • Play a vital role in managing the serving and routing backbone of a large enterprise Agentic AI platform, including hands-on experience with real on-premise GPU and multi-cloud model infrastructures.
  • Opportunities are available for strong candidates, regardless of current location, with the expectation of the ability to be based in Cairo and travel as engagement requires.
Apply Direct

Jobs you might like   View all jobs

About Business Consulting and Services Company

Company details are hidden. Subscribe to view full company profile.

Independent company profile

Information about this company and its job listings is independently compiled by Zero Tax Jobs from publicly advertised opportunities. Zero Tax Jobs is not affiliated with, sponsored by, endorsed by, or acting on behalf of this company.

Ready to apply for this role?

Apply Direct