Embedded AI Engineer, On-Device Models at Deepgram
Confirmed open
Adapt Deepgram speech models to embedded chips, DSPs and NPUs through custom kernels and device-specific optimization.
%22%20stroke%3D%22%23e2e8f0%22%20%2F%3E%0A%20%20%3Ctext%20x%3D%2240%22%20y%3D%2245%22%20text-anchor%3D%22middle%22%20font-family%3D%22ui-sans-serif%2C%20system-ui%2C%20-apple-system%22%20font-size%3D%2226%22%20font-weight%3D%22700%22%20fill%3D%22%230f172a%22%3EDE%3C%2Ftext%3E%0A%3C%2Fsvg%3E)
Deepgram- Location
- Remote
- Advertised region
- USA - Remote / United States
- Employment
- FullTime
- Work arrangement
- remote
- Technologies
- C++, Linux
Create a free application profile — Keep your skills and projects in a reusable profile. Private by default; you choose when to share. Apply for this job directly with the employer.
Role overview
This role writes C, C++ or Rust kernels and low-level operators for non-NVIDIA accelerators, quantizes and fuses model operations, and benchmarks latency, memory and power. It integrates vendor toolchains and delivers runtime components for embedded Linux, bare-metal or RTOS targets.
How to apply
Review the original posting and apply through the employer’s careers page.
View source and applyApply directlySource checked: 2026-10-11