GPU / AI Inference Engineer
Spectrum Solution W.L L
Visa & sponsorship
- Employers in Qatar sponsor the residence visa by default, and nothing in the posting says otherwise.
Job description
Job Summary:
We are seeking a GPU/AI Inference Engineer to deploy, optimize, and manage GPU-based AI model serving and inference infrastructure.
Key Responsibilities:
-
Configure NVIDIA GPU Operator, drivers, and GPU monitoring.
-
Deploy and optimize vLLM, LMCache, KServe, LiteLLM, and TEI/Infinity.
-
Manage AI model deployment, autoscaling, batching, and GPU scheduling.
-
Optimize inference performance, latency, throughput, and GPU memory utilization.
-
Implement GPU observability, workload orchestration, and cost tracking.
Required Skills:
-
Strong NVIDIA GPU, Linux, and Kubernetes experience.
-
Expertise in vLLM or similar AI inference frameworks.
-
Knowledge of GPU scheduling, model serving, and performance optimization.
-
Familiarity with LLM gateways, embeddings, rerankers, and Kueue.
Work Location: In person