About Interactly.ai

Interactly.ai is transforming healthcare operations with AI-powered automation across scheduling, lab follow-ups, eligibility checks, prior authorization, insurance verification, and more. Our multimodal AI agents work across voice, email, chat, fax, and EHR integrations—improving patient access, reducing staff burden, and accelerating care delivery. We already serve 2,000+ physicians and healthcare providers, delivering measurable outcomes such as 20–30% fewer no-shows and thousands of staff hours saved

Role Overview

We are seeking a Senior Backend Engineer – Real-Time Audio & Voice Systems to design, build, and operate low-latency, highly reliable voice and audio pipelines that power Interactly.ai’s conversational AI platform. This role requires deep hands-on experience with real-time audio streaming, speech-to-text (STT), text-to-speech (TTS), and telephony integrations, using Python and Node.js in production environments.

You will play a critical role in building scalable, fault-tolerant systems for high-volume voice interactions.

Key Responsibilities

- Design, develop, and operate real-time audio processing pipelines for conversational voice agents.
- Build and maintain backend services using Python (FastAPI/async frameworks) and Node.js for low-latency workflows.
- Implement bi-directional audio streaming using WebSockets, WebRTC,or similar protocols.
- Integrate and optimize Speech-to-Text (STT) and Text-to-Speech (TTS) engines (cloud-based or self-hosted).
- Build and maintain telephony integrations (inbound/outbound calling, call routing, call recording, DTMF, conferencing).
- Optimize audio latency, jitter, and reliability across distributed systems.
- Handle high-concurrency workloads and real-time session state management.




- Implement monitoring, logging, and alerting for voice pipelines and call flows.
- Collaborate with AI/LLM teams to integrate speech pipelines with conversational logic.
- Own production deployments, on-call rotations, and incident response for voice systems.

Required Qualifications

- 4+ years of backend engineering experience, with a strong focus on real-time systems.
- Strong hands-on experience with Python and Node.js in production environments.
- Proven experience building real-time audio or voice applications.
- Deep understanding of STT and TTS pipelines, audio codecs, and streaming concepts.
- Solid experience integrating telephony platforms (inbound/outbound calls, SIP, PSTN).
- Experience with WebSockets, WebRTC, or RTP-based streaming.
- Solid understanding of asynchronous programming and event-driven architectures.
- Experience with Docker and CI/CD pipelines.
- Ability to debug and optimize distributed, latency-sensitive systems.

Nice-to-Have Skills

- Experience with LLM-powered voice assistants and conversational AI systems.
- Familiarity with audio codecs (Opus, PCM, μ-law) and sampling strategies.
- Experience with cloud infrastructure (AWS/GCP) and autoscaling real-time services.
- Exposure to message queues, Redis, or real-time state stores.
- Prior experience in healthcare, contact centers, or telecom domains.

Why Join Interactly.ai?

- High-impact role: Own mission-critical voice infrastructure at scale.
- Challenging engineering problems: Build low-latency, real-time AI systems.
- Growth-stage startup: Influence architecture and technical direction from early stages.
- Global collaboration: Work closely with India- and US-based teams.
- Career progression: Opportunity to grow into Staff or Principal Engineering roles

📌 Senior Back End Developer - Real-Time Audio & Voice Systems (Hyderabad)
🏢 Interactly.ai
📍 Hyderabad