Where you can live
Open to people living in United States.
Listed location: USA - Remote
Taken from the location the company listed. Confirm in the posting before you apply.
What the job is
Writes and optimizes custom kernels and runtime code so Deepgram speech models run on non-NVIDIA chips, embedded SoCs, DSPs and NPUs.
What they ask for
- Write and optimize custom kernels and operators in C, C++, Rust, or platform assembly
- Optimize models for on-device targets via quantization, fusion, memory layout, and compilation
- Integrate with vendor NPU/DSP toolchains and edge inference runtimes
- Build performance-critical runtime code for embedded Linux, bare-metal, or RTOS targets
- Experience delivering production systems on resource-constrained hardware
Nice to have
- Real-time audio processing on embedded platforms, such as DSP pipelines or wake-word detection
- Depth in ML optimization like custom quantization or neural architecture search
- Hardware evaluation and benchmarking across accelerators or SoCs
This is a summary written by software from the company's posting. The posting is the source.
More remote jobs at Deepgram