Backend Engineer – LLM & Voice AI

Feather is a fast-moving startup dedicated to developing AI agents for the mortgage industry. Our mission is to revolutionize mortgage operations by automating tasks, enhancing efficiency, and delivering superior customer experiences. 📍 Remote (India) | 🕐 Full-Time | 💼 3+ Years Experience 🕸️ Website: www.featherhq.com 🧠 About Feather Feather is reimagining how businesses use voice. We’re building a conversational AI platform powered by LLMs, focused on replacing outdated IVR and call center systems with natural, human-like voice agents. Backed by top-tier VCs, we’re in beta with our first customers and scaling fast. We’re looking for a Backend Engineer who thrives across systems — from scalable APIs to inference pipelines — and wants to work on cutting-edge voice AI. You’ll help architect the backend infrastructure that powers real-time voice conversations, integrating LLMs and audio streaming tools like LiveKit. 🔧 What You’ll Do Build and scale core backend services for real-time voice AI Design APIs and event-driven systems to manage calls, sessions, and LLM interactions Work with OpenAI, LiveKit, and AWS to power voice agents at scale Develop job queues, data pipelines, and inference orchestration Optimize for low-latency, high-availability systems Contribute to system design, testing, and deployment automation Build and scale core backend services for real-time voice AI Design APIs and event-driven systems to manage calls, sessions, and LLM interactions Work with OpenAI, LiveKit, and AWS to power voice agents at scale Develop job queues, data pipelines, and inference orchestration Optimize for low-latency, high-availability systems Contribute to system design, testing, and deployment automation ✅ What We’re Looking For 3+ years of backend experience (preferably in TypeScript or Python) Strong understanding of system design, async architectures, and cloud infrastructure (AWS) Hands-on experience with LLM APIs (OpenAI, Langgraph, etc.) Comfort working across distributed systems, queues, and service boundaries Proactive, product-aware, and ready to take ownership 3+ years of backend experience (preferably in TypeScript or Python) Strong understanding of system design, async architectures, and cloud infrastructure (AWS) Hands-on experience with LLM APIs (OpenAI, Langgraph, etc.) Comfort working across distributed systems, queues, and service boundaries Proactive, product-aware, and ready to take ownership 🌟 Bonus Points Experience with LiveKit, Twilio, or voice streaming APIs Familiarity with speech-to-text (STT), text-to-speech (TTS), or WebRTC Knowledge of Temporal, LangGraph, or other workflow orchestration tools Experience building real-time apps or customer-facing tools Experience with LiveKit, Twilio, or voice streaming APIs Familiarity with speech-to-text (STT), text-to-speech (TTS), or WebRTC Knowledge of Temporal, LangGraph, or other workflow orchestration tools Experience building real-time apps or customer-facing tools 💼 What We Offer 💰 Competitive Salary + meaningful Equity 🌴 Paid vacation, plus national holidays 🤒 Flexible sick leave — no doctor’s notes required 🏡 Remote-first culture with flexible hours 🚀 Work directly with technical founders and help shape our roadmap 📈 Early-stage impact and growth path toward Tech Lead / Founding Engineer 💰 Competitive Salary + meaningful Equity 🌴 Paid vacation, plus national holidays 🤒 Flexible sick leave — no doctor’s notes required 🏡 Remote-first culture with flexible hours 🚀 Work directly with technical founders and help shape our roadmap 📈 Early-stage impact and growth path toward Tech Lead / Founding Engineer If you’re excited by the idea of building infrastructure that powers human-like AI agents — and want your work to ship fast and matter — we’d love to talk. Typescript Postgres MongoDb Langchain