Embedded AI Engineer, On-Device Models

📋 Description

• Take Deepgram's Speech/Convo models to embedded devices for on-device real-time inference.
• Optimize models for constrained targets via quantization, pruning, and distillation.
• Write and optimize performance-critical runtime code in C/C++/Rust for embedded platforms.
• Integrate with edge runtimes and vendor NPU/DSP toolchains for on-device mapping.
• Build on-device runtime plumbing: packaging, deployment, OTA updates, telemetry.
• Establish repeatable benchmarking across hardware to measure latency, power, memory.

🎯 Requirements

• Experience delivering production systems on resource-constrained hardware (embedded/mobile/edge AI).
• Strong C/C++/Rust skills with performance-critical code for constrained environments.
• Hands-on model optimization for on-device deployment (quantization, pruning, distillation, or specialized compilation).
• Familiarity with edge runtimes (ONNX Runtime/TensorRT/TFLite/ExecuTorch) and NPU/DSP toolchains.
• Strong HW/SW interaction knowledge: CPU/GPU/NPU/DSP, memory, fixed-point, power management.
• Experience with bare-metal/RTOS (FreeRTOS, Zephyr) and embedded Linux.