Apply Now

ML Acceleration Engineer

The World's Largest Social Network

Full time

Apply Now
Menlo Park, CA
Expected Pay Rate:
$117.00 - $127.00 per hour
Monday - Friday, 40 hours per week
Assignment Length:
1 year contract
Job Description

HireArt is helping the world's largest social network find an ML Acceleration Engineer to implement efficient acceleration of machine learning (ML) algorithms for computer vision in embedded domain, with an emphasis on performance and power. 

The ideal candidate will have strong software development skills; familiarity with machine learning algorithms like CNN’s; and hands-on experience in software/hardware codesign, especially in the context of machine learning.

As ML Acceleration Engineer, you will: 

  • Collaborate with computer architects, software, machine learning and silicon engineers, to map and optimize machine learning workloads on various backend targets including CPU’s, DSP’s, and deep learning accelerators.
  • Run analysis/profiling; identify performance and power bottlenecks on the actual hardware, virtual platforms, simulators, or emulators; and provide feedback for optimizations across the entire stack.
  • Work with deep learning compilers and identify the correct knobs for best efficiency and influence new feature additions.
  • Develop optimized kernels and port various machine learning libraries to backends, like DSP’s with custom ISA.
  • Ensure high quality by creating tests and automation infrastructure.
  • Partner with productization teams and driver/firmware teams to integrate machine learning acceleration into shipping software and create any new tools as necessary.
  • BS in electrical engineering/computer science, with MS or PhD preferred
  • 5+ years of industry experience
  • Strong coding skills in C/C++ or Python
  • Familiarity with profiling and debug tools
  • Experience with hardware acceleration on GPU’s/CPU’s/DSP’s/custom hardware
  • Familiarity with machine learning algorithms like CNN’s and frameworks like Tensorflow/Pytorch
  • Comfortable with reading others' code, tracing them, and code refactoring

Preferred qualifications: 

  • Knowledge of profiling and debug tools in context of machine learning
  • Familiarity with deep learning compilers like tensor-rt and XLA 
  • Understanding of machine learning algorithm optimizations for low power (e.g. quantization, pruning, etc.)

Commitment: This is a full-time (40 hours per week), 1-year contract position through HireArt and based in Menlo Park, CA.

HireArt values diversity and is an Equal Opportunity Employer. We are interested in every qualified candidate who is eligible to work in the United States. Unfortunately, we are not able to sponsor visas.