Java Developer

Overview

 Title: Backend Engineer/ Senior Backend Engineer – Agentic AI for Voice Platforms

Location: Chennai

Experience: 0 - 7 yrs

Type: Full-time

Role Overview

We are building an Agentic AI platform for voice-based customer support, integrating telephony, real-time audio streaming, LLMs, and backend orchestration. You will work on foundational backend components and service workflows that enable real-time AI-powered voice interactions, under the guidance of senior engineers. that powers real-time conversations, session management, call flows, scaling, reliability, and integrations with AI services.

This is a hands-on engineering role for someone who understands high-scale backend systems and can collaborate closely with AI engineers building the LLM/ASR/TTS layers.

Responsibilities

• Design and build high-throughput backend services for voice-based AI agents (call routing, session state, orchestration)

• Build APIs and services for: Telephony integration (SIP, WebRTC, PSTN providers like Twilio/Exotel/etc.)
• 
  
• Real-time streaming pipelines (audio in/out, event-driven flows).

• Orchestration of LLM, ASR, TTS services.

• Design low-latency, fault-tolerant services for handling live calls.

• Integrate with message brokers (Kafka/Pulsar), caching layers, and databases.

• Implement scalable concurrency models (async, reactive, or event-driven).

• Own production readiness: observability, retries, rate limiting, circuit breakers.

• Work closely with AI/ML engineers to productionize LLM pipelines.

• Contribute to architectural decisions around microservices vs event-driven vs streaming systems.

Must Have

• Strong backend engineering experience in Java (Java 17+, Spring Boot / Micronaut / Quarkus).

• Solid experience building high-concurrency networked services.

• Hands-on experience with distributed systems, messaging (Kafka, RabbitMQ), and caching (Redis).

• Python experience (required) – ability to collaborate on LLM pipelines, write glue services, or debug AI workflows.

• Good understanding of REST, gRPC, WebSockets, async processing.

• Experience with Docker, Linux, CI/CD.

• Strong fundamentals in system design & performance tuning.

Good to Have

• Experience with telephony / VoIP / WebRTC / SIP.

• Exposure to real-time media pipelines (audio streaming, RTP, MediaMTX, WebRTC SFU).

• Experience integrating with LLMs, ASR, TTS APIs (OpenAI, Whisper, Vosk, Coqui, etc.).

• Knowledge of cloud infra (AWS/GCP/Azure), load balancing, autoscaling.

• Understanding of event-driven architectures.

What You’ll Build

• A real-time AI voice agent backend handling thousands of concurrent calls

• Call flow engines, agent state machines, orchestration layers

Production-grade infra for AI-powered customer support automation