Senior Speech Software Engineer: Real-Time Voice at Scale

Lever, Inc.; New York (NY); Hybrid; USD 215,000 - 235,000; Full time

Job summary

ASAPP is seeking a Senior Speech Software Engineer to drive the infrastructure and applied speech intelligence behind our real-time voice AI platform. You will operate at the intersection of speech research, model optimization, and production engineering, ensuring ASR and TTS systems meet demanding quality, latency, and reliability requirements.

You will collaborate with Speech Scientists, ML Researchers, and Infrastructure Engineers to bridge cutting-edge speech technology with hardened

Qualifications

• 5+ years of software engineering in production-grade distributed systems.
• Proficiency in Go or Python; ability to design low-latency, high-concurrency systems.
• Experience with ASR and/or TTS or speech processing in production.

Responsibilities

• Tune ASR and TTS models for real-world call centers, improving transcription accuracy and robustness.
• Refine prosody and pacing to improve naturalness of spoken output.
• Balance latency vs. quality in streaming speech pipelines for real-time responsiveness.
• Architect scalable, high-availability voice infrastructure and modernize legacy systems.
• Design and operate streaming ASR → LLM → TTS pipelines powering live conversations.
• Develop tooling to monitor production performance and detect regressions in accuracy or latency.

Skills

Distributed systems

Go/Python

Low-latency design

Real-time media

Code optimization

Tools

Kubernetes

Docker

AWS

GCP

Azure

Job description

ASAPP is seeking a Senior Speech Software Engineer to drive the infrastructure and applied speech intelligence behind our real-time voice AI platform. You will operate at the intersection of speech research, model optimization, and production engineering, ensuring ASR and TTS systems meet demanding quality, latency, and reliability requirements.

You will collaborate with Speech Scientists, ML Researchers, and Infrastructure Engineers to bridge cutting-edge speech technology with hardened