Senior Researcher, Efficient Inference for Production ML

MLSys 2020; San Francisco (CA); On-site; USD 140,000 - 180,000; Full time

Job summary

MLSys 2020 in San Francisco is looking for a Senior Researcher specialized in machine learning efficiency. The role involves designing and researching methods for quantization, speculative decoding, and other efficiency techniques, ensuring that research translates into production.

The ideal candidate will have over 5 years of experience in related fields, strong statistical expertise, and proficiency in tools like PyTorch or Jax. Join our small team for impactful work on autonomous research agents.

Qualifications

• 5+ years of hands-on research experience in machine learning.
• Strong understanding of training and inference performance.
• Experience in translating research into production.

Responsibilities

• Research and develop quantization methods.
• Design and evaluate speculative decoding approaches.
• Investigate training-time efficiency methods.
• Run controlled experiments at production scale.
• Co-design methods with inference engineering.

Skills

Machine Learning Research

Quantization

Speculative Decoding

Distillation

Efficient Algorithms

Statistical Expertise

Written Communication

Education

PhD in ML or related field

Tools

PyTorch

Jax

Job description

MLSys 2020 in San Francisco is looking for a Senior Researcher specialized in machine learning efficiency. The role involves designing and researching methods for quantization, speculative decoding, and other efficiency techniques, ensuring that research translates into production.

The ideal candidate will have over 5 years of experience in related fields, strong statistical expertise, and proficiency in tools like PyTorch or Jax. Join our small team for impactful work on autonomous research agents.