Embedded AI Engineer (Voice AI)

TL;DR

Embedded AI Engineer (Voice AI): Optimizing and deploying speech and conversational models on resource-constrained embedded and edge hardware with an accent on performance-critical runtime code and hardware-software interaction. Focus on quantization, pruning, and architecture-specific compilation to meet strict latency, memory, and power budgets for real-time voice experiences.

Location: Must be based in the USA (Remote)

Salary: $219.3K – $274.1K base salary + bonus + equity

Company

Deepgram is a leading Voice AI platform providing real-time speech-to-text and text-to-speech APIs, powering voice offerings for over 1,300 organizations.

What you will do

• Define architecture for on-device, real-time inference across diverse processors and accelerators.
• Optimize models through quantization, pruning, distillation, and operator fusion.
• Write performance-critical runtime code in C, C++, or Rust for embedded environments.
• Integrate with edge inference runtimes and vendor NPU/DSP toolchains.
• Build on-device runtime plumbing including deployment pipelines and telemetry.
• Establish benchmarking and validation for latency, accuracy, and power consumption.

Requirements

• Must be based in the USA
• Experience delivering production systems on resource-constrained hardware.
• Strong proficiency in C, C++, or Rust for performance-critical code.
• Hands-on experience with model optimization for on-device deployment.
• Familiarity with edge inference runtimes like ONNX Runtime, TensorRT, or TFLite.
• Understanding of hardware-software interaction including CPU/GPU/NPU/DSP architectures.
• Experience working with bare-metal, RTOS, or embedded Linux environments.

Nice to have

• Experience with real-time audio processing and DSP pipelines.
• Depth in ML optimization techniques like custom quantization or neural architecture search.
• Background in hardware evaluation and benchmarking.
• Experience shipping AI features in consumer products at scale.

Culture & Benefits

• AI-first culture where AI tools are integrated into daily workflows.
• Fast-paced environment focused on experimentation and rapid adaptation.
• Competitive compensation including base salary, annual bonus, and equity.
• Opportunity to work on cutting-edge edge AI technology for consumer hardware.