Profile cover
D

AI Speaker Verification Anti-Spoofing Developer

Daniel Sokolov

Full-time · Job · Los_Angeles

About the role

Speaker verification — confirming that a voice belongs to a specific enrolled speaker — is a widely deployed biometric authentication mechanism. The adversarial threat is spoofing: presenting a synthesized or replayed voice that fools the verification system. As voice cloning technology has become more accessible, the anti-spoofing component of speaker verification has become the critical security layer that determines whether voice biometrics can be trusted in high-stakes authentication contexts. We build voice AI systems for 70 clients, several of whom deploy voice biometrics for financial services and healthcare authentication. Anti-spoofing is the security capability that makes those deployments defensible. Current spoofing attacks range from replay attacks (recording a legitimate user) to fully synthetic TTS-generated voices to voice conversion attacks that transform one speaker's voice to match another's. Each attack type has different acoustic signatures that require different detection approaches. You'll lead anti-spoofing system development: building detection models for each attack type, designing the ensemble architecture that handles multiple attack vectors simultaneously, and implementing the adversarial robustness evaluation that tests spoofing detection against new attack methodologies as they emerge.

Responsibilities

  • Build replay attack detection using channel and environment consistency analysis
  • Develop fully synthetic voice detection capturing spectral artifacts of TTS-generated audio
  • Implement voice conversion spoofing detection identifying naturalness anomalies in converted speech
  • Design ensemble architecture combining attack-specific detectors with a meta-classifier
  • Create adversarial robustness evaluation testing detection against new attack methodologies as they emerge
  • Monitor equal error rate across attack types as primary security quality metric

Requirements

  • 6+ years in speech ML or audio signal processing with speaker verification or anti-spoofing experience
  • Deep understanding of voice biometric systems, spoofing attack taxonomies, and ASVspoof challenge methodology
  • Strong Python and PyTorch skills with audio feature engineering and binary classification model development
  • Familiarity with voice conversion, TTS artifacts, and replay attack acoustic signatures
  • Experience building security-grade ML systems that meet financial services or healthcare authentication standards

Benefits

  • Fully remote with flexible schedule
  • Comprehensive health benefits
  • $4,000 annual professional development budget
  • Equity participation
  • Bonus tied to anti-spoofing equal error rate targets

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 statistics docker sql

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

Technical Writer

RemoteAI company

Part-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

Senior

Language

English

Salary Range

$130k – $160k / year

AI Expertise

AI & Machine Learning Engineers NLP & Prompt Engineering

Skills

python pytorch statistics docker sql aws

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