Senior Voice AI Platform Engineer
Aivar Innovations Private Limited2 months ago
Bengaluru, IndiaSenior
Responsibilities
- Own distributed real-time systems that orchestrate thousands of simultaneous voice calls.
- Improve calls-per-vCPU by extending Pipecat or rewriting hot-path components in Go.
- Decompose and optimize latency across STT, LLM, TTS, RAG, tool-calling, turn detection, and network hops.
- Diagnose pipeline failures and own fixes for call quality and reliability issues.
- Build voice-to-voice evaluations that gate releases and detect provider drift.
- Make STT, LLM, TTS, RAG, and tool-calling provider decisions based on quality and latency tradeoffs.
- Extend the platform into live assist, agent assist, and related products.
- Review code, mentor engineers, and define engineering standards.
Requirements
- 5+ years building production products and systems, including at least 2 years building and operating real-time voice AI in production.
- Deep understanding of the full voice pipeline and its effects on quality and latency.
- Strong Go and Python skills, with particular value placed on production-grade, performance-critical Go.
- Experience scaling Pipecat or a comparable real-time voice framework to high concurrency in production.
- Fluency in STT, LLM, TTS, RAG, and tool-calling provider tradeoffs.
- Experience building or running evaluations for real-time voice or LLM systems.
- Fluency with agentic coding tools and a measurement-driven approach to quality.
- Experience must extend beyond prompt engineering, managed voice platforms, CRUD backends, or ML model research.
Benefits
- Work arrangement: Bangalore office.