Description :

What Youll Work On :

You will work on building AI-powered voice applications, conversational agents, and GenAI-first product features. The role will involve backend development, API integrations, real-time audio workflows, and collaboration with product and engineering teams.

Key Responsibilities :

- Build and maintain backend services using Python

- Develop real-time Voice AI applications using Pipecat

- Integrate LLMs, STT, TTS, and voice streaming services

- Work with APIs, WebSockets, async processing, and low-latency systems

- Build GenAI features such as agents, tool calling, RAG, and conversational workflows

- Collaborate with frontend, product, and AI teams to ship high-quality features

- Work across the stack when needed using React / Next.js / TypeScript

- Write clean, scalable, and production-ready code

Must-Have Skills :

- 5+ years of software development experience

- Strong hands-on experience with Python backend development

- Mandatory experience with Pipecat

- Experience building Voice AI / conversational AI / AI agents

- Experience with GenAI application development using LLM APIs

- Good understanding of APIs, WebSockets, async programming, databases, and cloud deployments

- Experience with tools or services like OpenAI, Anthropic, Gemini, Azure OpenAI, Deepgram, ElevenLabs, Cartesia, Twilio, Daily, or similar

- Strong problem-solving and debugging skills

Good to Have :

- Experience with FastAPI, Django, Flask, Redis, PostgreSQL, MongoDB

- Experience with React, Next.js, TypeScript, or Node.js

- Exposure to LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or similar

- Experience with vector databases like Pinecone, Qdrant, Weaviate, Chroma, or pgvector

- Experience with Docker, AWS, GCP, Azure, or Kubernetes