Tacit
Senior Firmware Engineer, Edge AI / NPU Runtime
$150K–$210K
San Francisco · On-site · Senior · Full-time · Posted Jun 2, 2026
- Experience
- 5+ years in embedded firmware, embedded systems, or edge ML systems.
- Visa sponsorship
- Visa sponsorship
About the job
Develop and ship production firmware for neurotechnology hardware, including real-time sensor pipelines and optimized on-device AI inference.
What you'll do
- Deploy and optimize ML models and inference runtimes on embedded hardware accelerators.
- Build real-time sensor-to-inference pipelines with reliable, low-latency data movement.
- Debug and bring up production hardware, and optimize system performance, power use, and reliability.
What they ask for
- 5+ years of experience in embedded firmware, embedded systems, or edge ML systems.
- Strong C/C++/Rust experience on resource-constrained embedded platforms.
- Experience with RTOS-based systems such as FreeRTOS, Zephyr, ThreadX, or similar.
- Experience deploying or optimizing ML inference on embedded targets, NPUs, DSPs, MCUs, or edge SoCs.
Nice to have
- Experience with embedded inference runtimes, deployment toolchains, or edge AI SoCs/accelerators.
- Experience with quantized inference, fixed-point math, SIMD/DSP optimization, accelerator programming, or model conversion workflows.
Pay
$150,000 - $200,000/year (USD, base salary); $160K – $210K (USD, compensation; type not specified)
Tools
C/C++/Rust, FreeRTOS, Zephyr, ThreadX, DMA, TensorFlow Lite Micro, ONNX Runtime, CMSIS-NN
AI focus
On-device ML inference on embedded hardware, including model deployment, runtime integration, performance and power optimization, and collaboration on quantization and model tradeoffs.
Model-written summary · the original posting is authoritative