Location: Noida (Onsite) | Experience: 3-5 Years |

We are not looking for a Data Scientist who trains models in a notebook. We are looking for a Backend Engineer who builds real-time, bi-directional Voice AI agents.

You will build the "Brain and Ears" of our fintech voice bots, ensuring they can listen, think, and speak in under 800ms.

• The Pipeline: Architect full-duplex voice pipelines using WebSockets (not just REST APIs). Connect Twilio/Exotel streams to Deepgram/Whisper and LLMs in real-time.
• The Speed: Optimize Python code using asyncio to handle concurrent calls. If the bot lags, you fix it.
• The Logic: Move beyond simple "Chatbots." Build complex state machines (e.g., If user says 'Wait', stop talking immediately) using tools like LangChain or custom Python logic.
• The Stack: Integrate best-in-class Voice APIs (Deepgram, Google TTS, OpenAI Realtime API) and deploy them on AWS/GCP using Docker.

If you don't have these, please do not apply.

1. Python Frameworks: Mastery of FastAPI or Starlette. (Experience with only Django/Flask is not sufficient).
2. Real-Time Protocols: Deep understanding of WebSockets (wss://) and streaming audio data (bytes handling).
3. Concurrency: Proven experience with Async/Await (asyncio) in Python. You must know how to handle non-blocking I/O.
4. Voice Tech: Hands-on experience with ASR (Whisper, Deepgram, Google) and TTS (ElevenLabs, Azure, Polly).
5. LLM Integration: Experience building products with OpenAI API / Anthropic (Function Calling, System Prompts, JSON Mode).

• Experience with SIP Trunking (Twilio/Plivo/Exotel).
• Knowledge of Vector Databases (Pinecone/Qdrant) for RAG.
• Experience fine-tuning small models (Llama-3, Mistral) for specific tasks.
• Familiarity with Docker & Kubernetes for deployment.

Send your resume + A GitHub link to a project where you used WebSockets or LLMs. (Resumes without code samples will be prioritized last).

*For direct apply send your resume at singh.jyoti@cognitensor.com/ +91 8262004185*