Senior Inference ML Engineer: Transformers & Vision

Senior Inference ML Engineer: Transformers & Vision

Full-Time 135000 - 165000 $ / year (est.) On-site
W

At a Glance

  • Tasks: Adapt and optimize language and vision models for cutting-edge Cerebras hardware.
  • Company: Join Cerebras Systems, a leader in AI hardware innovation.
  • Benefits: Competitive salary, health benefits, and opportunities for professional growth.
  • Other info: Dynamic team environment with exciting projects and career advancement.
  • Why this job: Make a real impact on AI technology and work with top researchers.
  • Qualifications: Experience in machine learning and strong collaboration skills required.

The predicted salary is between 135000 - 165000 $ per year.

Cerebras Systems is seeking a Senior Research Engineer for the Inference ML team to adapt and optimize language and vision models for our Cerebras hardware.

You will collaborate with researchers and engineers to design, prototype, validate, and optimize end-to-end inference pipelines.

Responsibilities include advancing speculative decoding, pruning, compression, and sparse attention, training models to convergence, and profiling performance to deliver low-latency inference at scale.

#J-18808-Ljbffr

Senior Inference ML Engineer: Transformers & Vision employer: We Love AI Jobs

Cerebras Systems is an exceptional employer that fosters a collaborative and innovative work culture, where Senior Inference ML Engineers can thrive in the heart of cutting-edge technology. Located in a vibrant tech hub, employees benefit from continuous growth opportunities, competitive compensation, and a commitment to work-life balance, making it an ideal place for those looking to make a meaningful impact in the field of machine learning and AI.

W

Contact Details:

We Love AI Jobs Recruitment Team

We think you need these skills to ace Senior Inference ML Engineer: Transformers & Vision

Machine Learning
Natural Language Processing
Computer Vision
Model Optimization
End-to-End Inference Pipelines
Speculative Decoding
Pruning Techniques