Senior LLM Performance Engineer - Inference (Dubai)

Gateworth Group; Dubai; On-site; AED 420,000 - 660,000; Full time

Benefits offered by this job

Family benefits

Job summary

Gateworth Group is expanding its AI engineering capability in the UAE and building a team focused on large‑scale model performance. Senior engineers will work deeply in the internals of modern LLMs, optimise inference behaviour, and contribute to high‑performance model deployment across complex environments.

This role suits someone who enjoys highly technical work and understands transformer‑based models at scale, moving across research, engineering, and system‑level optimisation to shape

Responsibilities

• Analyse, profile, and optimise LLM inference performance across distributed, multi‑chip or multi‑node systems
• Apply deep understanding of transformer architectures, including dense and MoE models
• Evaluate and benchmark leading LLMs (LLaMA, Mistral, Qwen, DeepSeek) across different hardware environments
• Design and implement optimisations for attention mechanisms such as Flash Attention, grouped‑query attention, and sliding‑window attention
• Work on model‑level optimisation techniques including quantisation (INT8/FP8), KV‑cache management, batching, and parallelism strategies
• Collaborate with hardware, systems, and compiler teams to co‑design efficient inference pipelines
• Build and maintain benchmarking frameworks to evaluate latency, throughput, and scaling behaviour
• Analyse trade‑offs between model architecture choices and system‑level performance, contributing to deployment strategies for large‑scale environments
• Stay current with research in LLM architectures and inference optimisation

Skills

Transformer architectures

LLMs (LLaMA, Mistral, Qwen, DeepSeek)

MoE architectures

Attention mechanisms optimization

Inference optimization

Python & PyTorch/JAX

Distributed systems

Profiling performance

Systems thinking

Job description

Gateworth Group is expanding its AI engineering capability in the UAE and building a team focused on large‑scale model performance. Senior engineers will work deeply in the internals of modern LLMs, optimise inference behaviour, and contribute to high‑performance model deployment across complex environments.

This role suits someone who enjoys highly technical work and understands transformer‑based models at scale, moving across research, engineering, and system‑level optimisation to shape