about 8 hours ago
Remote, United StatesSenior / Mid Level
H1B Sponsor
Responsibilities
- Own the end-to-end voice AI architecture from Twilio media streams to TTS output.
- Design and implement multi-agent systems for complex patient workflows.
- Build and optimize real-time audio pipelines including WebSocket streaming.
- Architect analytics and observability infrastructure for voice metrics.
- Solve voice-specific challenges such as turn-taking and latency optimization.
- Integrate voice agents with internal services via secure APIs.
- Drive platform reliability and eliminate single points of failure.
- Collaborate with product and clinical operations to improve self-serve efficacy.
- Mentor team members on voice AI best practices.
Requirements
- 5+ years of software engineering experience, with at least 2 years in voice AI or conversational AI systems.
- Deep experience with voice AI pipelines from telephony through STT, LLM processing, and TTS.
- Production experience with agentic architectures and real-time conversation contexts.
- Strong understanding of voice-specific challenges like VAD tuning and latency budgets.
- Hands-on experience with telephony systems such as Twilio.
- Proficiency in TypeScript/Node.js and experience with async programming patterns.
- Experience with STT/TTS providers and understanding of ASR accuracy challenges.
- Production experience with LLM APIs and prompt engineering for conversational agents.
- High agency and autonomy in driving projects to completion.
- Excellent communication skills for translating complex architecture decisions.
Benefits
- Comprehensive medical, dental, vision, life, and disability plans for employees and dependents.
- Free testing for employees and their immediate families, along with fertility care benefits.
- Pregnancy and baby bonding leave, 401k benefits, and commuter benefits.
- Generous employee referral program.