Lead the design and implementation of a scalable, high-availability voice infrastructure that replaces legacy systems.
Build and refine multi-threaded server frameworks capable of handling thousands of concurrent, real-time audio streams with minimal jitter and latency.
Deploy robust ASR > LLM > TTS pipelines that process thousands of calls concurrently.
Develop robust logic for handling media streams, ensuring seamless audio data flow between clients and our ML models.
Build advanced monitoring and load-testing tools specifically designed to simulate high-concurrency voice traffic.
Partner with Speech Scientists and Research Engineers to integrate state-of-the-art models into a production-ready environment.

Requirements

5+ years of software engineering experience, with a proven track record of building and maintaining production-grade infrastructure.
A background in building ASR/TTS products at scale that interact with foundational LLMs.
Expert-level proficiency in Golang, Python, or willingness to learn.
Deep understanding of audio processing, including sample rates, codecs (Opus, G.711), network protocols, and buffering strategies.
Strong background in object-oriented design and the ability to architect systems that are both modular and performant.
The ability to navigate and refactor large existing codebases while transitioning to new, more efficient architectures.

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

GolangPythonASRTTSaudio processingobject-oriented designmulti-threaded server frameworksnetwork protocolsbuffering strategieshigh-concurrency systems

leadershipcollaborationproblem-solvingcommunicationarchitectural design