Senior Voice AI Engineer for Real-Time Speech Systems

ASAPP; New York (NY); On-site; USD 215,000 - 235,000; Full time

Job summary

ASAPP in New York City is seeking a Senior Speech Software Engineer to drive both the infrastructure and applied speech intelligence behind our real-time voice AI platform. This role sits at the intersection of speech research, model optimization, and production engineering, ensuring high quality, low latency, and reliability for enterprise call centers.

You will collaborate with Speech Scientists, ML Researchers, and Infrastructure Engineers to evolve our speech stack, tune modern models for

Qualifications

• 5+ years building production-grade distributed systems.
• Proficient in Golang or Python, with low-latency, high-concurrency experience.
• Experience with real-time streaming or media is preferred.

Responsibilities

• Tune ASR and TTS models for real-world call centers to improve accuracy and noise robustness.
• Architect scalable, low-latency voice infrastructure and streaming pipelines.
• Collaborate with Speech Scientists, ML Researchers, and Infra Engineers to productionize models.
• Define quality metrics and build monitoring for production speech systems.

Skills

Distributed systems

Golang

Python

Low-latency design

Tools

Kubernetes

Docker

AWS

GCP

Job description

ASAPP in New York City is seeking a Senior Speech Software Engineer to drive both the infrastructure and applied speech intelligence behind our real-time voice AI platform. This role sits at the intersection of speech research, model optimization, and production engineering, ensuring high quality, low latency, and reliability for enterprise call centers.

You will collaborate with Speech Scientists, ML Researchers, and Infrastructure Engineers to evolve our speech stack, tune modern models for