Job Description

Company Description

We’re building self-healing voice agents for enterprise customer support within ixigo. The system has to know when it’s failing, why it’s failing, and how to fix itself before a human notices. This fellowship sits at the intelligence layer behind that work.

Job Description

We need a founding engineer to own the voice AI product end to end: the cascaded pipeline that turns a phone call into a real-time conversation. This is not a research role and not a generic backend role. It is the person who understands, at the millisecond level, why a voice agent feels slow, where the latency actually lives across the STT, LLM, and TTS legs, and how to claw it back without breaking conversation quality.

You will have access to real production call traces and a live traffic testing ground from day one. Decisions you make ship to real customer-facing calls within days, not quarters.

What you'll own

• The end-to-end latency budget across the cascaded pipeline (STT finalization, LLM prefill and generation, TTS time-to-first-byte), with a target of sub-1-second end-to-end response time
• Diagnosing and fixing cross-cutting bottlenecks that touch multiple pipeline legs at once, for example, prompt size and cache-hit rate degrading prefill time, network payload, and throughput contention simultaneously
• Evaluating and integrating STT/LLM/TTS providers (including in-region India options) against the latency and quality bar, and building the abstraction layer that keeps us model-agnostic and provider-swappable
• Turn detection, interruption and barge-in handling, filler audio, and retry logic, the mechanics that make a bot feel like it is actually listening
• Instrumentation and tracing across the full call lifecycle so every latency regression is diagnosable from data, not guesswork
• Making the build vs. buy call on pipeline components as the product scales beyond the current reference customer

Non-negotiable

You have hands-on, production experience optimizing a cascaded voice pipeline or voice harness, meaning STT, LLM orchestration, and TTS stitched together into a live conversational system, not a single-model or text-only pipeline. You can talk concretely about where latency hides in each leg, what trade-offs you made between accuracy and speed, and what broke when you pushed the system harder. If your voice AI experience is limited to calling a hosted conversational API (Twilio Voice, a managed voicebot platform) without touching the pipeline internals, this is not a fit, regardless of years of experience elsewhere.

Other requirements

• 3-5 years minimum building and operating production systems at scale, with real on-call or ownership experience, not just feature delivery
• Strong systems fundamentals: concurrency, network I/O, profiling, and the instinct to measure before optimizing
• Comfortable working with ambiguous, partially-specified problems and real production data rather than clean specs
• Direct, low-ego communication. You will get short, blunt feedback and are expected to push back with data when you disagree

Strong nice-to-haves

• Experience with WebRTC, telephony infrastructure (SIP/PSTN), or real-time audio streaming
• Familiarity with prompt caching mechanics and how prefill cost scales with context length
• Experience in a founding or very early-stage (pre-seed to seed) environment where you owned a system with no safety net

Additional Information

Responsible for safeguarding sensitive company data against unauthorized access, use, or disclosure, and for reporting any suspected security incidents in line with the organization's ISMS (Information Security Management System) policies and procedures.