Description:

Contribute to the design, development, and implementation of the core Voice Platform including Audio Acquisition, Conversation Management, and Speech Generation.
Partner with product managers to understand customer use cases and technology challenges.
Build and deploy large Voice AI distributed systems at scale across multiple regions and datacenters.
Enforce best practices in software engineering architecture and processes, including code reviews and unit testing.
Improve SRE practices by turning operational use cases into software tooling requirements.
Mentor colleagues and promote knowledge-sharing across Voice AI engineering disciplines.

Requirements:

8+ years of relevant industry experience.
Hands-on experience building distributed Voice AI systems at large operational scale.
4+ years of experience building LLM-based applications (integrating models, not training).
6+ years of development experience with Python, Golang, Java, or similar languages.
2+ years of experience in prompt engineering and developing LLM-based experiences.
Experience operating highly available distributed workloads on Kubernetes with a DevOps approach.
Experience in compliance and security in regulated environments is a plus.
Proven track record of architecting and shipping distributed Voice AI systems at scale.
Familiarity with AI tools such as Claude Code, Cursor, Windsurf.

Skills