Python & PyTorch Compiler Engineer (AI Inference)

Cerebras; Dubai; On-site; AED 330,000 - 441,000; Full time

Job summary

A leading AI technology firm in Dubai seeks talented individuals to join its Inference Team. You will engage in developing and optimizing generative models to harness the power of Cerebras' unique wafer-scale AI architecture. This role demands strong proficiency in Python and extensive knowledge of PyTorch. You will drive innovations in inference speeds and model optimization in a collaborative and dynamic environment. Embrace the opportunity to contribute to groundbreaking advancements in artificial intelligence.

Benefits

Job stability with startup vitality

Research publication opportunities

Cutting-edge technology

Qualifications

• Degree in Engineering, Computer Science, or equivalent experience.
• Strong Python programming skills and in-depth experience with PyTorch internals.
• Solid understanding of computational graphs and tensor operations.

Responsibilities

• Analyze generative AI models and understand impacts on the compilation stack.
• Develop model definition framework for large language models.
• Extend and optimize PyTorch-based tools for graph transformation.

Skills

Python programming

PyTorch internals

C++ programming

Model optimization

Understanding of computational graphs

Education

Degree in Engineering or Computer Science

Tools

PyTorch

TensorFlow XLA

HuggingFace Transformers

MLIR

Job description

A leading AI technology firm in Dubai seeks talented individuals to join its Inference Team. You will engage in developing and optimizing generative models to harness the power of Cerebras' unique wafer-scale AI architecture. This role demands strong proficiency in Python and extensive knowledge of PyTorch. You will drive innovations in inference speeds and model optimization in a collaborative and dynamic environment. Embrace the opportunity to contribute to groundbreaking advancements in artificial intelligence.