Model Optimization Engineer - Dubai

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs, offering industry leading training and inference speeds and simplifying large scale ML application deployment.

Our wafer scale architecture delivers the compute power of dozens of GPUs on a single chip with the programming convenience of a single device, enabling fast, efficient run of generative AI models.

About the Role

Join the Cerebras Inference Team to develop the fastest generative models inference in the world, working at the intersection of hardware, compiler, and ML framework to optimize for the Cerebras platform.

Job Responsibilities

• Analyze emerging generative AI models and techniques, assess their implications for optimization.
• Design, implement, and evaluate novel model optimization algorithms for large scale neural networks.
• Research and develop methods that enhance inference efficiency and performance on Cerebras systems.
• Collaborate closely with hardware, compiler, and ML framework teams to drive end to end optimization improvements.
• Benchmark, profile, and document results to inform future architecture and software decisions.

Requirements

• Degree in Computer Science, Engineering, or related field, or equivalent practical experience with demonstrated exceptional ability.
• Strong foundation in machine learning theory, algorithms, and optimization techniques.
• Proven experience developing high performance ML workloads using Python, and either Triton or CUDA for GPU or accelerator programming.
• Proficiency with PyTorch and Hugging Face Transformers, including experience fine tuning or deploying large language models (LLMs).
• Understanding of model compression, quantization, distillation, and sparsity techniques.

Preferred Qualifications

• Experience optimizing models for specialized hardware (e.g., GPUs, TPUs).
• Publication record or open source contributions in model optimization, efficient inference, or compiler based ML acceleration.
• Strong analytical and experimental skills, with the ability to translate research insights into production level implementations.

Why Join Cerebras

• Build a breakthrough AI platform beyond GPU constraints.
• Publish and open source cutting edge AI research.
• Work on one of the fastest AI supercomputers in the world.
• Enjoy job stability with startup vitality.
• Experience a simple, non corporate work culture that respects individual beliefs.

Equal Opportunity Statement

Cerebras Systems is committed to creating an equal and diverse environment and is proud to be an equal opportunity employer. We celebrate different backgrounds, perspectives, and skills. Inclusive teams build better products and companies.