Description
Deepgram is hiring an Embedded AI Engineer on its Partner Platform Engineering team to write and optimize custom kernels, operators, quantization, and assembly-level code for non-NVIDIA accelerators, embedded SoCs, DSPs, and NPUs. The role owns target-side model optimization, integrates with vendor inference runtimes, builds performance-critical runtime components, establishes platform benchmarks, and partners with silicon and platform vendors. It is intended for a senior embedded engineer or a staff-level engineer, with experience in constrained hardware, C/C++/Rust, model optimization, and embedded systems.
