Profile cover
E

AI Overlapping Speech Separation Engineer

Elena Cohen

Full-time · Job · Chicago

About the role

Python, PyTorch, and clean audio feature pipelines are the core of what our speech team builds every day. Our diarization and voice activity detection models already label who's speaking well when people take turns, but the moment two speakers talk over each other, both our transcription and diarization quality drop sharply. This role builds separation models that isolate overlapping voices into distinct audio streams before the rest of the pipeline ever sees the recording.

Responsibilities

  • Build source separation models for overlapping speech segments
  • Integrate separated audio streams into the existing diarization pipeline
  • Benchmark separation quality against real multi-speaker recordings
  • Work with the ASR team to measure downstream transcription improvement

Requirements

  • Strong background in audio source separation or speech processing
  • Experience with PyTorch and TensorFlow for audio modeling
  • Familiarity with real-world multi-speaker recording conditions
  • Comfortable evaluating models with both objective and listening tests

Benefits

  • Fully remote position
  • Competitive salary and equity
  • Health and dental insurance
  • Conference and learning budget

Keep exploring related roles

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

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$130k – $160k / year

AI Expertise

NLP & Prompt Engineering AI & Machine Learning Engineers

Skills

python pytorch tensorflow statistics

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

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

Apply — create free profile