Deepgram
Embedded AI Engineer, On-Device Models
US
UTC-10 to UTC-5 $219k to $274k per year Full time
Mid level
- Where you can live
- USA - Remote
- Working hours
- Overlap with UTC-10 to UTC-5
- Salary
- USD 219,300 to 274,100 per year
- Posted
- July 7, 2026
Summary from the posting
Deepgram's speech models are among the fastest and most accurate in the world, and we have deep machinery for running them on NVIDIA GPUs. Our customers need them on everything else: non-NVIDIA accelerators, embedded SoCs, mobile application processors, DSPs and NPUs, and purpose-built devices with tight memory, compute, thermal, and power budgets. When a target platform's standard kernels and runtime can't run a Deepgram model well enough, someone has to go below them. That is this role.
As an Embedded AI Engineer on the Partner Platform Engineering team, you work at the lowest layer of our edge stack.
This is a short summary. The full description, requirements and the application form are on Deepgram's own career page.