Senior Voice AI Engineer — Convogent Delivery

1 month ago

Bengaluru, India or Coimbatore, IndiaMid Level / Senior

Responsibilities

Own customer delivery outcomes from discovery through production go-live within committed timelines.
Customize and configure Convogent using Pipecat and LiveKit for customer telephony, CRM, knowledge-base, compliance, and use-case requirements.
Engineer real-time audio pipelines and optimize STT and TTS flows for latency, concurrency, and call quality.
Troubleshoot production voice systems across capture, STT, orchestration, and TTS, and drive issues through resolution.
Connect STT, TTS, and LLM agents into resilient, observable workflows with appropriate guardrails.
Translate customer requirements into deployable solutions and scope, size, and iterate use cases against measurable outcomes.
Contribute to sprint tracking, status reporting, and stakeholder governance for owned use cases.

3–5 years of experience in the relevant engineering domain.
Hands-on experience building and deploying voice agents with Pipecat, LiveKit, or similar frameworks across multiple production deployments.
Deep expertise with STT technologies including Deepgram, Whisper, AssemblyAI, Google STT, or Sarvam, and TTS technologies including ElevenLabs, Cartesia, or Amazon Polly.
Working knowledge of speech-to-speech services including Amazon Nova Sonic, multi-speaker diarization, and conversation segmentation.
Production fluency in Python plus at least one of Node.js, TypeScript, or Go.
Practical experience with TensorFlow, PyTorch, or Scikit-learn; conversational AI design; prompt engineering; and LLM integration with GPT-4o, Claude, or Bedrock models.
Cloud deployment experience on AWS with Docker, Kubernetes, and CI/CD, including services such as Lambda, EC2, S3, EKS, Polly, Transcribe, and Bedrock.
Ability to scope, prioritize, and deliver work under SOW or contract constraints across live customer engagements.
Ability to manage multiple concurrent customer engagements with differing requirements, technology stacks, and stakeholders.
Preferred: customer delivery, consulting, or systems integration experience; exposure to regulated industries; enterprise stakeholder management; low-code voice platform experience; voice analytics; transcription tooling; Indian-language STT/TTS models; or AWS and speech technology certifications.

Full-time role based in Coimbatore or Bangalore.
Work directly on production systems and live enterprise customer engagements.
End-to-end ownership from discovery through production go-live.
Direct interaction with enterprise technical stakeholders.
Opportunity to work with Aivar’s production voice AI accelerator and enterprise customer base.

51-200 employees