Senior AI Performance Engineer - Hardware & ML Acceleration

MBR Partners; Dubai; On-site; AED 300,000 - 500,000; Full time

Benefits offered by this job

Relocation tickets (incl. family)

Visa support

Insurance

Job summary

MBR Partners in Dubai is seeking an AI Performance Engineer to profile and optimize AI workloads across hardware platforms. You will evaluate ML frameworks, tune models, and collaborate with software/firmware teams to meet end-to-end performance goals. Strong C and Python, DL framework internals, and distributed systems experience are essential.

Relocation, visa, and insurance are provided. Join a fast-growing innovator in AI hardware delivering high-performance infrastructure for researchers

Qualifications

• 5 years of experience with C and Python
• Hands on experience the internals of deep learning frameworks (e.g. PyTorch TensorFlow)
• Experience with training and deployment of ML models
• Experience with distributed systems development
• Knowledge of best-practices in software development (testing, profiling, debugging, documentation, version control)
• Deep understanding of CPU/GPU/ASIC architectures and low-level optimization techniques

Responsibilities

• Profile and enhance the performance of AI workloads across hardware platforms and ML frameworks
• Identify workloads and micro-benchmarks for performance analysis
• Follow industry trends in AI algorithms and evaluate them on company hardware
• Experiment with model optimization techniques (quantization, pruning, compression)
• Diagnose and troubleshoot complex heterogeneous computing systems and software issues
• Collaborate with software and firmware teams to meet end-to-end performance goals

Skills

C programming

Python

PyTorch

TensorFlow

LLM development

Distributed systems

Performance profiling

Job description

MBR Partners in Dubai is seeking an AI Performance Engineer to profile and optimize AI workloads across hardware platforms. You will evaluate ML frameworks, tune models, and collaborate with software/firmware teams to meet end-to-end performance goals. Strong C and Python, DL framework internals, and distributed systems experience are essential.

Relocation, visa, and insurance are provided. Join a fast-growing innovator in AI hardware delivering high-performance infrastructure for researchers