Founding Engineer - Voice AI
ixigo (company site, opens in a new tab)3–5 yrsDelhi NCROn-siteDirect career pageEst. 20–35 LPA
Posted 2h ago
Reach people at ixigo
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at ixigo you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Own the end-to-end latency budget across STT, LLM and TTS, targeting sub-1-second responses without sacrificing conversation quality.
- Diagnose cross-pipeline bottlenecks; evaluate providers and build swappable integrations, plus turn detection, interruption, retries and call-lifecycle tracing.
- Use production call traces and live traffic to ship improvements quickly and make build-versus-buy decisions as the product scales.
Minimum Requirements
- Work Experience Required: 3–5 years minimum building and operating production systems at scale, including real on-call or system ownership.
- Mandatory: Hands-on production experience optimizing a cascaded voice pipeline or voice harness combining STT, LLM orchestration and TTS; hosted voice APIs alone do not qualify.
- Strong systems fundamentals in concurrency, network I/O and profiling, with experience measuring and optimizing production behavior.
Ideal Candidate Profile
- Has concrete experience locating latency across STT finalization, LLM prefill/generation and TTS, and balancing speed against accuracy under load.
- Fits an end-to-end systems ownership role where changes reach live customer calls quickly and optimization is guided by traces and production data.
- Experience with WebRTC, SIP/PSTN, real-time audio streaming, prompt caching or an early-stage environment is a plus.