Senior Software Engineer, Python & Silicon Engineering

Mythic

Redwood City, CA, USA

Full time

Apr 22

This job is no longer accepting applications.

About the AI Engineering Team:

Mythic is enabling the future of AI by building an analog-compute hardware platform that is 10-100x more efficient than conventional all-digital systems. Mythic’s AI hardware combines knowledge across many domains, including AI, compilers, and chip design. This vision comes together in the AI Engineering team, where our expertise is used to develop AI algorithms and models that are optimized for our hardware, as well as to provide guidance to Mythic’s hardware and compiler teams. If innovation at the intersection of AI and hardware sounds exciting to you, this role is for you. 

The AI Engineering team significantly impacts Mythic by:

• Developing quantization and robustness AI retraining tools

• Co-design new features with our compiler team that leverage the adaptability of neural networks to maximize speed & efficiency

• Developing new neural networks that are optimized for our hardware products

• Interfacing with internal and external customers to meet their development needs


About the AI Silicon Engineering Team:

This team bridges the gap between hardware and AI by controlling and characterizing analog compute hardware for the purpose of running neural newtorks. This requires building an understanding of hardware, signal processing, and neural networks, and bringing these techniques together to have a fully integrated Neural Network <=> Analog Computing system.

The AI Silicon Engineering team significantly impacts Mythic by:

• Characterizing and modeling Mythic's analog compute hardware for use inside of a PyTorch training environment.

• Developing flash cell programming algorithms for use with neural networks.

• Developing production quality debug algorithms for trouble-shooting Mythic's software and hardware stack.

• Creating analog compute tolerance requirements for hardware components - this impacts the design cycle of other teams.

• Running neural network inference on-chip and analyzing gaps between the models and large-scale silicon runs.


This role is not location specific. However, candidates will be expected to keeping working hours in line with either Pacific or Central Time.

Here's what you will do:

  • Develop internal software for analyzing neural network silicon accuracy and isolate deviations from simulation models.
  • Develop internal software for characterizing Mythic's analog compute hardware.
  • Develop customer-facing software to health check analog compute.
  • Work directly with internal and external customers to incorporate feedback and feature requests.
  • Learn how Mythic’s custom hardware works and build support for new features.

Here's the background we hope you have:

  • 5+ years of software experience in a production environment
  • 3+ years of Python experience
  • Experience writing code to interact with hardware
  • Experience working directly with internal and/or external customers
  • Bachelor's degree in Computer Science or related field
  • Strong communication skills, both written and spoken

The following would be nice to have, but is not required

  • Experience working on complex problems with algorithm-heavy code
  • Experience working with silicon bringup
  • Experience with neural network applications
  • Experience with PyTorch, ONNX, and standard numeric/scientific libraries
  • Contributions to open-source software
  • MS/PhD in Computer Engineering, Computer Science, or Electrical Engineering


You must be logged in to to apply to this job.

Apply

Your application has been successfully submitted.

Please fix the errors below and resubmit.

Something went wrong. Please try again later or contact us.

Personal Information

Profile

View resume

Details

Mythic

Moving edge AI to a new level with a revolutionary analog compute-in-memory technology.

{{notification.msg}}