Senior Inference ML Engineer — Sparse Attention & Pruning

Cerebras; Canada; Hybrid; CAD 100,000 - 150,000; Full time

Job summary

A leading AI technology company is seeking a Senior Research Engineer to enhance inference models for its innovative hardware. The ideal candidate will possess advanced skills in Python or C++, along with significant experience in machine learning and AI technologies. This role involves designing and optimizing transformer architectures, leading research on inference algorithms, and collaborating across teams. Applicants must have a strong educational background in computer science, with several years of hands-on experience in the field. This hybrid role can be based in Toronto, ON, or Sunnyvale, CA.

Benefits

Open-source AI research

Job stability with startup vitality

Non-corporate work culture

Qualifications

• 7+ years of ML software development experience.
• Experience testing and maintaining software products for 4+ years.
• 3+ years of experience in machine learning software development.

Responsibilities

• Design and implement transformer architectures for NLP and computer vision on Cerebras hardware.
• Research novel inference algorithms and model architectures.
• Profile and optimize model code to maximize throughput.

Skills

Programming skills in Python

Programming skills in C++

Experience with Generative AI

Understanding of transformer-based models

Education

Bachelor's degree in Computer Science or related field and 7+ years of experience

Master's degree in Computer Science or related field and 4+ years of experience

PhD in Computer Science or related field with 2+ years of experience

Tools

PyTorch

Transformers

vLLM

SGLang

Job description

A leading AI technology company is seeking a Senior Research Engineer to enhance inference models for its innovative hardware. The ideal candidate will possess advanced skills in Python or C++, along with significant experience in machine learning and AI technologies. This role involves designing and optimizing transformer architectures, leading research on inference algorithms, and collaborating across teams. Applicants must have a strong educational background in computer science, with several years of hands-on experience in the field. This hybrid role can be based in Toronto, ON, or Sunnyvale, CA.