GenAI Inference Compiler Engineer

Cerebras; United Arab Emirates; On-site; AED 293,000 - 441,000; Full time

Job summary

A leading AI hardware company in the UAE is seeking a Software Engineer to develop cutting-edge inference solutions for generative models. Candidates should have a degree in Engineering or Computer Science, strong skills in Python and C++, and experience with AI tools like PyTorch. This role offers the chance to work on groundbreaking AI technology while enjoying a non-corporate work culture focused on diverse perspectives.

Qualifications

• Strong experience working with Python and C++ languages.
• Understanding of Transformer architecture variations and generation cycles.
• Evidence of exceptional ability in relevant fields.

Responsibilities

• Analyze new generative AI models and related impacts on compilation stack.
• Implement compiler and frontend features to support new models.
• Collaborate with teams throughout feature implementation.
• Research methods for model optimization to enhance inference.

Skills

Python

C++

Experience with PyTorch

Experience with HuggingFace Transformers

Knowledge of MLIR based compilation stack

Education

Degree in Engineering, Computer Science or equivalent experience

Job description

A leading AI hardware company in the UAE is seeking a Software Engineer to develop cutting-edge inference solutions for generative models. Candidates should have a degree in Engineering or Computer Science, strong skills in Python and C++, and experience with AI tools like PyTorch. This role offers the chance to work on groundbreaking AI technology while enjoying a non-corporate work culture focused on diverse perspectives.