Senior AI Engineer

Client of Gateworth Group; Dubai; On-site; AED 420,000 - 640,000; Full time

Job summary

Gateworth Group is partnering with a UAE-based technology organization expanding its AI engineering team to push large-scale model performance. You will dive deep into transformer internals, optimize LLM inference across multi-chip and multi-node systems, and help shape deployment strategies for large-scale AI infrastructure.

The role focuses on benchmarking, profiling, and implementing optimisations for attention mechanisms, quantisation and KV caching, collaborating with hardware and compiler

Qualifications

• Hands-on experience with modern LLMs and transformer internals.
• Experience with multi-chip or multi-node inference.
• Strong Python and ML framework skills.
• Experience with quantisation, pruning, KV caching, batching, and parallelism.

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 hardware environments
• Design and implement optimisations for attention mechanisms such as Flash Attention and sliding window attention
• Work on model level optimisation techniques including quantisation, pruning, KV caching, 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 for deployment strategies for large-scale environments
• Stay current with research in LLM architectures and inference optimisation

Skills

Transformer architectures

MoE architectures

Python programming

Distributed systems

Performance profiling

Tools

PyTorch

JAX

Job description

Overview

Gateworth Group is supporting a technology organisation in the UAE that is expanding its AI engineering capability and building out a specialised team focused on large scale model performance. The company is investing heavily in advanced AI systems and is hiring senior engineers who can work deep 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, understands how transformer based models behave at scale and can move comfortably between research, engineering and system level optimisation. You ll work across model analysis, performance tuning, benchmarking and architecture decisions, helping shape next generation AI infrastructure.

Main 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 Mixture of Experts 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

Qualifications

• Strong understanding of transformer architectures and LLM internals
• Hands on experience with multiple modern LLMs (LLaMA, Mistral, Qwen, DeepSeek)
• Deep knowledge of dense and Mixture of Experts (MoE) architectures
• Familiarity with attention mechanisms and their optimisation strategies
• Experience with inference optimisation techniques (quantisation, pruning, KV caching, batching)
• Strong Python skills and experience with ML frameworks such as PyTorch or JAX
• Experience with distributed systems and large scale inference workloads
• Ability to profile and debug performance bottlenecks across hardware and software stacks
• Strong systems thinking with the ability to work across model, runtime, and hardware layers

Preferred

• 8+ years experience in deep learning, AI systems, or performance engineering
• Experience working close to hardware
• Familiarity with parallelism strategies (tensor, pipeline, expert parallelism)
• Experience with datacenter scale deployment and inference servers (e.g., vLLM)
• Background in performance engineering or systems optimisation