AI Inference Engineer

DubaiRemote OK5–10 yrsFull-time

Responsibilities

Define and build the AI inference serving strategy and architecture from first principles to handle high-throughput, latency-sensitive workloads. Own the model-level optimization strategy and integrate low-level GPU/CUDA performance work into the serving layer.

Requirements

Requires 4+ years of experience building large-scale inference serving systems with deep expertise in optimization techniques like quantization and batching. Candidates must possess strong systems thinking and the ability to operate independently in a founding role.

Key skills

AI Inference ServingCUDAGPU Performance OptimizationvLLMTensorRT-LLMSGLangTriton Inference ServerQuantizationSpeculative DecodingKV-Cache ManagementRequest RoutingAutoscalingSystems ArchitectureKubernetesSlurmDistributed Systems

Benefits

Competitive Salary

Equity Sign-on Bonus

Biannual Bonus Scheme

Fully Expensed Tech

Breakfast And Dinner Allowance

Apply now

You'll apply on the employer's official page.