Python & PyTorch Compiler Engineer — Fastest AI Inference

Cerebras; United Arab Emirates; On-site; AED 367,000 - 515,000; Full time

Job summary

A leading AI technology company in the United Arab Emirates is seeking experts in generative AI model inference. You will work on optimizing unique software and hardware combinations to achieve top inference speeds. Required qualifications include a degree in Engineering or Computer Science and strong programming skills in Python, particularly with PyTorch. Join us to be part of groundbreaking advancements in AI and enjoy a supportive, non-corporate work environment.

Benefits

Job stability with startup vitality

Open-source AI research opportunities

Non-corporate work culture

Qualifications

• Exceptional ability in Engineering or Computer Science.
• In-depth experience with PyTorch internals.
• Experience with ML graph optimization frameworks.

Responsibilities

• Analyze new generative AI models for impact on compilation.
• Develop and maintain frontend compiler infrastructure.
• Collaborate with teams for feature implementation.

Skills

Python programming

PyTorch internals

Computational graphs

Compiler optimization

C++ extensions

Large Language Models

ML and compiler collaboration

Education

Degree in Engineering or Computer Science

Tools

PyTorch

HuggingFace Transformers

Job description

A leading AI technology company in the United Arab Emirates is seeking experts in generative AI model inference. You will work on optimizing unique software and hardware combinations to achieve top inference speeds. Required qualifications include a degree in Engineering or Computer Science and strong programming skills in Python, particularly with PyTorch. Join us to be part of groundbreaking advancements in AI and enjoy a supportive, non-corporate work environment.