about 2 hours ago
Remote, Worldwide or New York, NY, USAMid Level / Senior / Staff+
H1B Sponsor
Base Salary
$219k - $274k/yr
Responsibilities
- Optimize Deepgram's speech models for embedded and low-power consumer hardware.
- Write performance-critical runtime code in C, C++, and/or Rust for embedded environments.
- Integrate with edge inference runtimes and vendor NPU/DSP toolchains.
- Establish benchmarking and validation processes across target hardware.
- Collaborate with silicon and device vendors for SDK integration and performance tuning.
- Work with Research and Engine teams to influence model architectures for edge deployment.
Requirements
- Experience delivering production systems on resource-constrained hardware.
- Strong proficiency in C, C++, and/or Rust for performance-critical code.
- Hands-on experience with model optimization techniques for on-device deployment.
- Familiarity with edge inference runtimes and vendor-specific toolchains.
- Strong understanding of hardware-software interaction and its impact on performance.
- Experience in bare-metal or RTOS environments, embedded Linux, or edge SoC development.