Profile cover
D

AI Wake Word Detection Engineer

Daniel Sokolov

Full-time · Job · Los_Angeles

About the role

Every voice assistant starts with a wake word. 'Hey Aria', 'OK Nova', 'Wake up' — the decision to activate or stay silent runs on a model deployed directly on device, operating continuously at 50mW, with a false acceptance rate that needs to stay below 1 per 4 hours of ambient audio. Too sensitive and users get random activations at dinner. Not sensitive enough and the assistant misses half of legitimate invocations. You'll build and optimize the wake word detection models for our enterprise voice assistant platform. The models run on ARM microcontrollers and low-power DSPs — every kilobyte of model size and every milliwatt of power consumption matters. You'll work on keyword spotting architectures, quantization techniques for on-device inference, and the negative mining pipelines that collect hard false positives from field deployments. The role is hybrid: 2 days per week in our Santa Clara acoustic testing lab for hardware-in-the-loop experiments, 3 days remote. The speech team is six engineers; you'll own the on-device detection pipeline.

Responsibilities

  • Design and train keyword spotting models optimized for on-device inference
  • Apply quantization and compression techniques to meet device memory and power constraints
  • Build hard negative mining pipelines from field deployment audio
  • Evaluate models against false acceptance rate and false rejection rate targets
  • Collaborate with firmware team on runtime integration for target device architectures
  • Benchmark detection performance across noise environments and speaker demographics

Requirements

  • 3+ years in speech ML with on-device or edge deployment experience
  • Hands-on experience with keyword spotting or speaker verification models
  • Strong understanding of quantization, pruning, and edge inference frameworks
  • PyTorch or TensorFlow proficiency with knowledge of TFLite or ONNX Runtime
  • Familiarity with acoustic feature engineering: MFCCs, mel spectrograms

Benefits

  • Hybrid: 2 days in Santa Clara lab, 3 days remote
  • Health, dental, and vision insurance
  • 401(k) with match
  • $3,000 annual hardware and conference budget
  • Patent incentive program

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

AI & Machine Learning Engineers NLP & Prompt Engineering

Skills

python pytorch tensorflow docker aws

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Senior Product Security Engineer

RemoteAI company

Full-time Senior

Senior AI Researcher- Pre-training (f/m/d)

RemoteAI company

Full-time Senior

Drone Platform Integration & Network Support Engineer

RemoteAI company

Full-time

AI Resident UK/EMEA

RemoteAI company

Full-time

Senior AI R&D Engineer – Model Training (f/m/d)

RemoteAI company

Full-time Senior

Senior Machine Learning Engineer (Clinical Team)

RemoteAI company

Full-time Senior

Job Type

Full-time

Level

Mid-Level

Language

English

Salary Range

$100k – $130k / year

AI Expertise

AI & Machine Learning Engineers NLP & Prompt Engineering

Skills

python pytorch tensorflow docker aws numpy

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile
Create free account & apply Log in

Interested in this role? Create your free profile to apply.

Apply — create free profile