Engineering Manager, Voice AI & Real-Time Systems (Hybrid)

Theron Solutions; San Francisco (CA); Hybride; USD 210 000 - 270 000; Plein temps

Résumé du poste

Theron Solutions is seeking an accomplished Senior Software Architect to lead the architecture and deployment of a Voice AI agent platform. You will guide real‑time streaming, LLM orchestration, and system reliability while mentoring a growing team.

Responsibilities include collaborating with product and design to plan future capabilities and ensure scalable, low‑latency experiences across voice and chat channels in a hybrid (Redwood City, CA) environment.

Qualifications

• 8–15 years of experience in software engineering, building and operating complex, production‑grade systems.
• 3+ years leading software engineering teams.
• Experience building real‑time, low‑latency systems (e.g., streaming, WebSockets).
• Experience with LLM‑powered applications in production.
• Active daily use of AI coding assistants (e.g., Cursor).
• Experience with voice infrastructure (WebRTC, STT/TTS pipelines).
• Drives agile delivery through chaos and fast‑paced environments.

Responsabilités

• Lead the architecture and development of our client's Voice AI agent platform across voice, chat, and multi‑channel experiences.
• Contribute to system design, code reviews, and implementation with focus on LLM orchestration and real‑time streaming pipelines.
• Manage, mentor, and guide a team of software engineers and support their growth.
• Own the technical direction for agent reliability including session lifecycle management and automated degradation strategies.
• Collaborate with product and design teams to plan future initiatives and translate customer needs into agent capabilities.

Connaissances

Lead software architecture

Team leadership

Real-time streaming

LLM-powered apps

Formation

BS/MS CS or related

Outils

WebRTC

STT/TTS pipelines

LLM orchestration

Streaming frameworks

Description du poste

Theron Solutions is seeking an accomplished Senior Software Architect to lead the architecture and deployment of a Voice AI agent platform. You will guide real‑time streaming, LLM orchestration, and system reliability while mentoring a growing team.

Responsibilities include collaborating with product and design to plan future capabilities and ensure scalable, low‑latency experiences across voice and chat channels in a hybrid (Redwood City, CA) environment.