Elijah Scheele

Amateur mycologist, VP Engineering @ Drift Biotechnologies

Eli has been a functional programming zealot since 2017, when he discovered the joys of Elm and Elixir. An avid technologist, Eli likes to poke and prod all sorts of different technologies to see how they work - and to share the results of his experiments with anyone who’ll listen. In addition to his professional work designing distributed High Performance Computing (HPC), Eli tries to blend all of his passions for technology, arts, crafts, and accessibility in his personal projects.

Distributed Computational Workloads with Nx and Nerves

Deciding where your computational models will run has become more complicated with the rise of low-cost and low-power ML model accelerators. In this talk, we’ll explore how to distribute your computational workloads using distributed Erlang, benchmarking these systems, new opportunities unlocked by edge device inference, and how patterns from Nx and Nerves can be extended to new classes of devices.

Talk objectives:

  • Learn how to apply Elixir tools and techniques for distributing your computational workloads across a wide variety of devices.

Target audience:

  • Data Scientists
  • Infrastructure Engineers
  • Edge/IoT Device Makers