Full Stack Engineer (Real-Time Audio Systems) – Voice AI at Remote only Full Time

Job Title: Full Stack Engineer (Real-Time Audio Systems) – Voice AI

Location: Remote

Experience: 4+ Years

Employment Type: Full-time

About the Role

We’re looking for an experienced engineer to lead the development of a real-time Voice AI platform. This role blends deep expertise in conversational AI, audio infrastructure, and full-stack systems, making you a key contributor to building natural, low-latency voice-driven agents for complex healthcare workflows and beyond.

You’ll work directly with the founding team to build and deploy production-grade voice AI systems.

If you love working with WebRTC, WebSockets, and streaming pipelines, this is the place to build something impactful.

Key Responsibilities

• Build and optimize voice-driven AI systems integrating ASR (speech recognition), TTS (speech synthesis), and LLM inference with WebRTC and WebSocket infrastructure.
• Orchestrate multi-turn conversations using frameworks like Pipecat with memory and context management.
• Develop scalable backends and APIs to support streaming audio pipelines, stateful agents, and secure healthcare workflows.
• Implement real-time communication features with low-latency audio streaming pipelines.
• Collaborate closely with research, engineering, and product teams to ship experiments and deploy into production rapidly.
• Monitor, optimize, and maintain deployed voice agents for high reliability, safety, and performance.
• Translate experimental AI audio models into production-ready services.

Requirements

• 4+ years of software engineering experience with a focus on real-time systems, streaming, or conversational AI.
• Proven experience building and deploying voice AI, audio/video, or low-latency communication systems.
• Strong proficiency in Python (FastAPI, async frameworks, LangChain or similar).
• Working knowledge of modern front-end frameworks like Next.js (preferred).
• Hands-on experience with WebRTC, WebSockets, Redis, Kafka, Docker, and AWS.
• Exposure to healthcare tech, RCM, or regulated environments (highly valued).

Bonus Points

• Contributions to open-source audio/media projects.
• Experience with DSP, live streaming, or media infrastructure.
• Familiarity with observability tools (e.g., Grafana, Prometheus).
• Passion for reading research papers and discussing the future of voice communication.