Senior ai engineer – voice agent (ivr & llm integration)

About the Company

R Systems is a global product engineering and digital solutions provider. We combine complex engineering, Data & AI, cloud-native capabilities with deep domain understanding to design and build innovative products for Tech, Saa S platforms and enterprises across industry verticals. We leverage the power of Automation and Agentic AI to transform value chains to boost productivity and deliver differentiated customer experiences. With a culture of co-creation and an extensive partner ecosystem, we help customers navigate market shifts and drive sustained strategic growth.

About the Role

We’re seeking a seasoned Senior AI Engineer to lead the development of an intelligent, automated voice agent capable of handling real-time customer conversations. This role blends telephony integration, speech recognition, LLM orchestration, and backend API connectivity to deliver seamless, human-like interactions.

Responsibilities

Design and build voice-first AI systems that connect phone calls to STT, LLM, and TTS pipelines.

Integrate telephony platforms (Twilio, Vonage, SIP, Asterisk, Free SWITCH) with real-time voice workflows.

Implement STT / TTS solutions using Whisper, Amazon Transcribe, Google Speech, or Azure Cognitive Services.

Orchestrate LLMs using Lang Chain, Llama Index, or equivalent frameworks to manage prompts, tools, and function calls.

Develop robust APIs to write conversation outcomes into internal systems and trigger downstream actions.

Ensure low-latency, scalable architecture for real-time voice interactions.

Collaborate cross-functionally with product, design, and backend teams to align on goals and deliverables.

Monitor and optimize performance across voice latency, transcription accuracy, and LLM response quality.

Implement SQL-based reporting for conversation analytics and system health.

Qualifications

8–10 years of engineering experience, with at least 3 years in voice AI or conversational systems.

Required Skills

Proven expertise in telephony stack integration : Twilio, Vonage, SIP, Asterisk, Free SWITCH.

Hands-on experience with STT / TTS engines : Whisper, Amazon Transcribe, Google Speech, Azure TTS.

Deep understanding of LLM orchestration frameworks : Lang Chain, Llama Index, or custom prompt tooling.

Strong backend development skills in Python, Node.js, or similar, with API design and integration.

Experience with SQL databases and reporting pipelines.

Familiarity with event-driven architectures, webhooks, and real-time data flows.

Excellent problem-solving, communication, and stakeholder management skills.