Voice AI Engineer — Convogent Delivery

Keka Technologies Private Limited; Bengaluru; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

Aivar Innovations is hiring a Senior Voice AI Engineer to take voice AI use cases from discovery through live production for enterprise clients. You’ll work inside customer delivery pods, tailoring Convogent to diverse telephony stacks and CRM integrations, while ensuring timely delivery and measurable outcomes on live calls.

This hands-on role requires expertise in STT, TTS, S2S, and LLM integration, plus Python and at least one of Node.js, TypeScript, or Go.

Qualifications

• Hands-on experience building and deploying voice agents with Pipecat, LiveKit, or similar frameworks across production deployments.
• Deep expertise in STT (Deepgram, Whisper, AssemblyAI, Google STT, Sarvam) and TTS (ElevenLabs, Cartesia, Amazon Polly).
• Working knowledge of Speech-to-Speech services and how they impact pipeline design.
• Experience with multi-speaker diarization and conversation segmentation.
• Production fluency in Python and at least one of Node.js, TypeScript, or Go.
• Experience with AI/ML libraries and LLM integration for conversational AI.

Responsibilities

• Own customer delivery outcomes and ensure production-ready deployment within timelines.
• Customize and configure Convogent to fit customer telephony stacks and integrations.
• Engineer real-time audio pipelines for production with optimized STT and TTS flows.
• Troubleshoot live production systems and drive fixes to resolution.
• Build and adapt the orchestration layer to connect STT, TTS, and LLM agents.
• Translate customer requirements into deployable solutions with stakeholders.
• Report and govern delivery with sprint tracking and governance.

Skills

Pipecat

LiveKit

STT

TTS

S2S

LLM Integration

Python

Node.js

TypeScript

Go

Docker

Kubernetes

AWS

CI/CD

Tools

Docker

Kubernetes

AWS

CI/CD

Job description

3 to 10 Years | Coimbatore/ Bangalore |Full-Time

About Aivar Innovations

Aivar Innovations is an AI-native services and software company and an AWS Preferred Partner, backed by Bessemer Venture Partners and Sorin Investments. We ship production-grade AI into enterprise environments across fintech, healthcare, and technology. Our work is anchored by four accelerator platforms: Convogent (voice and agent AI automation), Velogent (governed agentic process automation for regulated industries), Kubogent (Kubernetes-native AIOps), and Datagent (data and analytics). We measure ourselves by what runs in production, not by slideware.

Role Overview

We are hiring a Senior Voice AI Engineer for Aivar's Delivery organization to take voice AI use cases from discovery through live production for our enterprise customers. You will build and customize voice agents on top of Convogent — Aivar's voice AI accelerator — working directly within customer engagements, delivery timelines, and SOW commitments. This is a hands-on engineering role embedded in customer-facing delivery pods, partnering closely with Delivery Managers, Solution Architects, and customer technical stakeholders to ship measurable outcomes on live calls.

What You'll Do

• Own customer delivery outcomes. Take voice AI use cases from discovery through production go-live within committed timelines, working inside Rocketlane-tracked delivery plans alongside your Delivery Manager.
• Customize and configure Convogent. Adapt Aivar's voice AI accelerator (built on Pipecat, LiveKit) to each customer's telephony stack (Twilio, Exotel, Cisco, Vonage, etc.), API/MCP integrations with customer CRM tools, knowledge base (KB) integrations, compliance constraints, and use-case requirements.
• Engineer real-time audio pipelines for production. Optimize STT and TTS flows for the latency, concurrency, and call quality bar each customer engagement demands.
• Troubleshoot customer production systems. When a live call does not sound right, quickly narrow down where in the pipeline it broke — capture, STT, orchestration, or TTS — by asking the right questions, reading the right signals, and driving the fix through to resolution.
• Build and adapt the orchestration layer. Connect STT, TTS, and LLM agents into resilient, observable workflows with guardrails suited to the customer's risk and compliance profile.
• Translate customer requirements into deployable solutions. Work directly with customer technical stakeholders alongside Aivar's SA and DM to scope, size, and iterate use cases against measurable outcomes — success rate, latency, adoption.
• Report and govern delivery. Contribute to sprint tracking, status reporting, and stakeholder governance for the use cases you own.

What You'll Bring

• Hands-on experience building and deploying voice agents with Pipecat, LiveKit, or similar frameworks — ideally across multiple distinct production deployments, not a single system.
• Deep expertise in STT (Deepgram, Whisper, AssemblyAI, Google STT, Sarvam) and TTS (ElevenLabs, Cartesia, Amazon Polly).
• Working knowledge of Speech-to-Speech (S2S) services, including Amazon Nova Sonic, and how they change pipeline and orchestration design compared to cascaded STT/LLM/TTS.
• Experience with multi-speaker diarization and conversation segmentation.
• Production fluency in Python plus at least one of Node.js, TypeScript, or Go.
• Practical use of AI/ML libraries (TensorFlow, PyTorch, Scikit-learn) and conversational AI design — prompt engineering and integration with LLMs (GPT-4o, Claude, Bedrock models).
• Cloud deployment experience on AWS (Lambda, EC2, S3, EKS, Polly, Transcribe, Bedrock) with Docker, Kubernetes, and CI/CD.
• Demonstrated ability to work under SOW/contract constraints — scoping, prioritizing, and shipping within a defined timeline and budget across live customer engagements.
• Comfort working across multiple concurrent customer engagements with differing requirements, tech stacks, and stakeholders.

Preferred Experience

• Prior experience in a customer delivery, consulting, or systems integration role, rather than purely product/platform engineering.
• Exposure to regulated industries (fintech, healthcare, BFSI) and their compliance and security constraints.
• Experience with enterprise stakeholder management — running status calls, translating technical tradeoffs into business language.
• Familiarity with low-code voice platforms alongside custom infrastructure.
• Voice analytics, transcription tooling, and Indian-language STT/TTS models.
• AWS or speech technology certifications.

Why This Role, Why Aivar

• Work that ships to real customers. Every use case you build runs live on enterprise calls, measured by customer outcomes, not demos.
• Own delivery end-to-end. From discovery call to production go-live, you are the engineering owner of the customer's voice AI outcome.
• Build on accelerators that work. Convogent has real production traction — you configure and extend a working platform across diverse customer environments.
• Direct customer exposure. Work face-to-face with enterprise technical stakeholders, not just internal teams.
• Backed and proven. AI-native, AWS Preferred Partner, BVP- and Sorin-backed, with 100+ enterprise customers in the first year.

Required Skills: Pipecat, LiveKit, STT, TTS, S2S, Conversational AI, LLM Integration, Customer Delivery, Production Troubleshooting

Required Skills

Pipecat STT LiveKit LLM Conversational AI LLM Integration TTS