About the role
Adapt Deepgram speech models to edge devices and non-NVIDIA accelerators. The work covers operator changes, quantisation, accuracy and latency benchmarking, and repeatable deployment onto constrained hardware. You will collaborate with embedded engineers on custom kernels; production Python and PyTorch experience matters.
Remote: United States.
Employer posting date: 2026-09-14.
Skills
How to apply
Apply directly on the employer's application page. Your application goes straight to them.
More from Deepgram
-
Senior Analytics Engineer, Decision Intelligence
Deepgram US only
$185K - $240K per year -
Security Engineer
Deepgram US only
$150K - $245K per year -
Staff Product Designer, Conversational AI
Deepgram US only · United States; Pacific Time, San Francisco preferred
$180K - $240K per year -
Director, Text-to-Speech Synthesis Research
Deepgram US only
$213K - $328.3K per year
Jobs like this
-
Staff Machine Learning Scientist
Dave US only · United States, except Hawaii
$208K - $269K per year -
Software Engineer, New Grad, Machine Learning Platform
Quora North America · United States or Canada
$97.6K - $139K per year -
Senior/Staff Credit Data Scientist
Splash Financial US only · United States
$143K - $220K per year -
Senior Data Scientist, Platform
Coinbase US only · United States
$180.4K - $212.2K per year
Republished listing
This opportunity was discovered on Deepgram's public careers page and is republished here for discovery purposes. Applications are handled by the employer.
If this is your role and you want it off the board, contact us.