Find your next role
Discover roles across ambitious teams
20,349 jobs
- More jobs
Deepgram
Applied ML Engineer, Edge Devices
Remote · USA · Mid level
$155k–$245k / year
About the role
Adapt Deepgram speech models to run efficiently on non-NVIDIA and edge hardware platforms. Own deployment and validation of models on real devices ensuring accuracy and latency.
What you’ll do
• Port speech models to non-NVIDIA and edge platforms. • Own model decisions for edge targets including quantization and operator substitution. • Validate ports on real hardware with benchmarks. • Build deployment pipelines for edge targets. • Collaborate with Embedded AI Engineers on custom kernels.
What you’ll bring
• Experience deploying ML models to edge or non-NVIDIA hardware. • Knowledge of quantization and precision tradeoffs. • Experience with edge inference runtimes and conversion toolchains. • Ability to modify model graphs and operators. • Strong Python and PyTorch skills with production-quality engineering habits. • Work authorization for USA.
Life at Deepgram
AI-first mindset with rapid change and innovation. Encourages experimentation and continuous learning.
About Deepgram
Deepgram provides real-time APIs for speech-to-text and voice AI, powering over 1,300 organizations with advanced voice-native foundation models.