Job Description

Roles & Responsibilities

As a Backend Engineer, you'll build the core systems behind our voice AI agents. You'll architect the real-time pipelines that process live speech, orchestrate LLM-powered conversations, manage concurrent voice sessions at scale, and ensure every call is fast, reliable, and intelligent. This means working hands-on with real-time audio processing, speech-to-text and text-to-speech pipelines, LLM orchestration, telephony (SIP/Asterisk), and distributed backend infrastructure. You'll work daily with Python, FastAPI, Pipecat, LiveKit (WebRTC), Celery, PostgreSQL, Redis, and Kubernetes.

What You'll Do

Build and optimize real-time voice AI pipelines — speech recognition (STT), LLM processing, and speech synthesis (TTS) running in sub-second loops

Design and maintain the backend services that manage voice agent sessions, call routing, and telephony integration (SIP/Asterisk)

Architect multi-agent orchestration systems — conversation flows, agent hand-offs, and context passing between voice AI agents

Build and scale the infrastructure for handling thousands of concurrent voice calls with low latency

Develop and optimize WebSocket and WebRTC-based real-time communication layers

Implement and manage distributed task processing for batch calling campaigns, call analytics, and post-call AI analysis

Architect, optimize, and maintain PostgreSQL databases, Redis caching, and message queues

Implement observability across voice pipelines: latency tracking, call quality metrics, distributed tracing (OpenTelemetry, Sentry)

Handle production debugging of real-time voice systems — diagnosing audio quality issues, latency spikes, and session failures

Work closely with AI, product, and DevOps teams to ship voice AI features end-to-end

Who You Are

Strong proficiency in Python with deep understanding of async/await and real-time concurrency patterns

Experience building production backend systems with FastAPI or similar async frameworks

Deep understanding of PostgreSQL, relational database design, and ORM patterns

Experience with real-time systems — WebSockets, streaming, audio pipelines, or low-latency communication

Hands-on experience with distributed task processing (Celery, Redis)

Comfortable owning production systems end-to-end, from design to deployment to incident response

Thrive in fast-paced, high-ownership environments where voice AI is the core product

Nice to Have

Experience with voice AI, conversational AI, or speech processing (STT, TTS, VAD)

Experience with telephony systems (SIP, Asterisk, WebRTC)

Familiarity with AI/LLM orchestration (OpenAI, LangChain, LangGraph, Pipecat, Livekit)

Experience with real-time audio frameworks or voice bot platforms

Cloud infrastructure experience (AWS, GCP, Kubernetes)

Vector databases and RAG patterns for knowledge-powered voice agents

Backend Engineer - Voice AI Platform Hams.ai

Backend Engineer - Voice AI Platform
Hams.ai