Inference Compiler and Frontend Engineer – Dubai

Cerebras Systems; United Arab Emirates; On-site; AED 120,000 - 200,000; Full time

Job summary

A leading AI technology company in Dubai is seeking an Inference Compiler and Frontend Engineer to develop software and hardware solutions. The role involves analyzing generative AI models, implementing features to optimize inference, and collaborating across teams. Candidates should have a degree in Engineering or Computer Science, and strong experience with Python and C++. Join us to work with cutting-edge AI technologies and a non-corporate culture that values individual beliefs.

Benefits

Work on one of the fastest AI systems

Opportunity to publish and open-source AI research

Startup vitality with job stability

Non-corporate work culture

Qualifications

• Demonstrated ability in a relevant engineering field.
• Experience with Python and C++ development.
• Familiarity with machine learning frameworks such as PyTorch.

Responsibilities

• Analyze new generative AI models and their impact.
• Implement compiler features to support new models.
• Collaborate across teams for feature development.
• Research optimization methods for Cerebras inference.

Skills

Python

C++

Knowledge of Large Language Models

Knowledge of MLIR-based compilation stack

Experience with PyTorch

Experience with HuggingFace Transformers

Education

Degree in Engineering or Computer Science

Job description

Overview

Inference Compiler and Frontend Engineer – Dubai

Cerebras Systems builds the world's largest AI chip and enables fast inference and training for large-scale ML applications. The Cerebras wafer-scale inference platform provides unprecedented speed for Generative models with a hardware architecture designed for fast local memory access, ultra-fast interconnect, and abundant compute.

About the Role

Join the Cerebras Inference Team to help develop a unique Software and Hardware combination with best-in-market inference characteristics while running the largest models available. You will work with the latest open and closed generative AI models to optimize for the Cerebras platform, focusing on model representation, optimization, and the compilation stack to deliver optimal results on current and future Cerebras systems.

You will be part of a team that collaborates across multiple disciplines to implement features that enhance model inference performance on Cerebras hardware.

Job responsibilities

• Analyze new models from the generative AI field and understand impacts on the compilation stack
• Implement compiler and frontend features to support new models, improve inference characteristics, and enhance the Cerebras user experience
• Collaborate with other teams throughout feature development
• Research new methods for model optimization to improve Cerebras inference

Requirements

• Degree in Engineering, Computer Science, or equivalent experience with demonstrated ability
• Strong experience with Python and C++
• Experience with PyTorch and HuggingFace Transformers
• Knowledge of Large Language Models and Transformer architectures
• Knowledge of MLIR-based compilation stack is a plus

Why Join Cerebras

We build a breakthrough AI platform beyond the constraints of the GPU. Our team highlights include:

• Work on one of the fastest AI systems in the world
• Publish and open source cutting-edge AI research
• Experience startup vitality with job stability
• Non-corporate work culture that respects individual beliefs

Apply for this job

Interested in joining Cerebras Systems? Apply to be considered for this role.

Cerebras Systems is committed to creating an equal and diverse environment and is proud to be an equal opportunity employer. We celebrate diverse backgrounds, perspectives, and skills and strive to empower people to do their best work through continuous learning and support.

This website or its third-party tools process personal data. For more details, review our CCPA disclosure notice.

Voluntary Self-Identification

For government reporting purposes, we ask candidates to respond to the below self-identification survey. Completion is voluntary and will not influence hiring decisions. Any information provided will be confidential.

As set forth in Cerebras Systems’s Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under applicable law. This includes VECRA/VEVRAA-related veteran status information and disability status as described in the Voluntary Self-Identification forms.