Principal / Staff Software Engineer

Nykaa · Bengaluru

  • Experience8–12 yrs
  • SalaryNot disclosed
  • Work modeonsite
  • Posted28 Sept 2026
Apply for this job

About Nykaa

Nykaa is hiring in Bengaluru in ecommerce retail. This role looks for around 8+ years of experience.

Skills

  • ASR/TTS
  • LLM orchestration
  • function calling
  • RAG
  • low-latency ML serving
  • real-time systems
  • streaming systems
  • audio processing
  • LLM evaluation
  • observability

The role

A generative AI engineer at an e-commerce company builds real-time voice systems using ASR/TTS and LLM orchestration, with function calling, RAG, and low-latency ML serving. Evaluation and observability for non-deterministic systems further define the work.

Full job description

Responsibilities:

A streaming, cascaded voice pipeline (ASR LLM TTS) with end-to-end response latency under ~800ms and a credible path toward the ~500-600ms range where callers stop noticing they're talking to AI.

Turn-taking and barge-in that feel human - semantic endpointing, interruption handling, and full-duplex audio - not naive VAD silence timers.

An evaluation and observability stack for voice: latency budgets per stage, transcription, hallucination and instruction-following evals, and replayable call traces.

The orchestration layer: tool/function calling, RAG over customer knowledge, guardrails, and graceful fallback when a model or vendor degrades.

Requirements:

Deep, hands-on experience building real-time or streaming systems - voice, video, RTC, audio, or low-latency ML serving.

You understand where milliseconds go.

Working knowledge of the modern agent stack: LLM orchestration, function/tool calling, streaming token pipelines, ASR/TTS, and how to evaluate non-deterministic systems.

You've shipped something users talked to (or otherwise interacted with in real time) and made it fast and reliable.