D
$219,300 – $274,100
Listed on Deepgram’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
This role involves optimizing Deepgram's voice AI models to run efficiently on embedded hardware and non-NVIDIA accelerators through custom kernel development, quantization, and low-level tuning. It suits experienced embedded systems engineers who thrive solving hard optimization problems under tight resource constraints and want to make large models viable on small devices.
Our summary, not Deepgram’s wording. The full posting is on their site.
Skills this role names
Log in to see which of these are already on your profile.
What they ask for
Required
- Production experience on resource-constrained hardware
- Proficiency in C, C++, or Rust
- Experience optimizing models for on-device deployment
- Familiarity with edge inference runtimes or vendor NPU/DSP toolchains
- Understanding of hardware-software interaction and memory hierarchies
- Experience in bare-metal, RTOS, or embedded Linux environments
- Strong communication and problem-scoping skills
Nice to have
- Real-time audio processing on embedded platforms
- Deep knowledge of ML optimization techniques like custom quantization
- Hardware benchmarking and accelerator evaluation experience
- Shipped AI features in consumer products at scale
- Familiarity with model compilation toolchains
- Experience with secure on-device deployment practices