Embedded AI Engineer, On-Device Models
Core
Optimizing speech AI models for deployment on resource-constrained edge hardware like embedded SoCs, DSPs, and NPUs.
Role type
Senior Embedded AI Engineer (On-Device Models)
Builds
Custom kernels, operators, and runtime components for edge inference
Domain
Edge AI / Embedded Systems / Speech Technology
Deliverable
production ML models
Required skills
C, C++, Rust, model quantization, operator fusion, bare-metal programming, RTOS development, hardware-software co-design, performance profiling, vendor toolchain integration
Preferred skills
Experience with non-NVIDIA accelerators, knowledge of ISA manuals, experience with cold-start optimization, power/thermal management
Technologies
C, C++, Rust, ONNX Runtime, TensorRT, TFLite, ExecuTorch, embedded Linux, RTOS
Responsibilities
Write and optimize custom kernels and operators for specific hardware; perform target-side quantization and assembly-level tuning; integrate with vendor NPU/DSP toolchains; build performance-critical runtime code; establish per-platform benchmarking and validation; partner with silicon vendors on SDK integration.
Seniority
Senior, hands-on IC
