Principal Engineer

SaaS Labs, Inc; Bengaluru; On-site; INR 600,000 - 1,200,000; Full time

Job summary

JustCall, SaaS Labs' flagship product, seeks a Principal Engineer to own the architecture of next-generation voice agents at scale. You’ll drive end-to-end design from the telephony edge to model orchestration, targeting latency, reliability, and strong observability across the stack.

You’ll lead real-time systems work, craft human-like turn-taking and full‑duplex audio, and shape the evaluation and integration framework that quantifies agent quality and safety in production.

Qualifications

• Deep, hands-on experience building real-time or streaming systems - voice, video, RTC, audio, or low-latency ML serving.
• 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 in real time and made it fast and reliable.

Responsibilities

• Own the architecture of JustCall's next-generation voice agents end-to-end.
• Develop a streaming voice pipeline with latency targets and robust end-to-end performance.
• Design turn-taking, barge-in, and full-duplex audio experiences.
• Build an evaluation and observability stack for voice with traces and latency budgets.
• Create an orchestration layer for tool calls, RAG, guardrails, and graceful fallbacks.

Skills

Real-time systems

LLM orchestration

Voice tech stack

Job description

Why This Role Matters

JustCall is the communication layer for tens of thousands of revenue teams - calls, SMS, and increasingly AI voice agents that talk to customers in real time. We've earned a decade of scale. We've also inherited a decade of architecture: a large PHP/JavaScript surface area, an integrations layer that's hard to extend, and a voice stack built for a pre-LLM world.

We are not looking for people to staff a backlog. We are looking for a handful of engineers who have already built systems at scale, who can walk into a ten-year-old codebase and a green-field voice-agent problem in the same week, and who want the rare thing: full ownership of a hard problem, with the autonomy and the equity to match.

If you read the four problems below and feel the itch to start sketching the design, this is for you.

Tracks

Every Principal Engineer shares the bar above. Tracks describe where you'll start and the depth we'll index on. Strong candidates often blur two tracks - that's welcome.

Track A - Voice & Agent Platform Principal Engineer

Your charter. Own the architecture of JustCall's next-generation voice agents end-to-end, from the telephony edge to the model orchestration to the evaluation harness that tells us whether an agent is actually good.

What you'll own in your first 6–12 months

• 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.

Must-haves

• 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.

Track B - Platform & Integrations Principal Engineer

Your charter. Re-imagine how JustCall connects to the outside world - CRMs, helpdesks, dialers, webhooks, and the long tail of partner APIs - as a resilient, observable, self-serve platform rather than a pile of bespoke connectors.

What you'll own in your first 6–12 months

• A redesigned integrations platform: a typed connector framework, a sync/eventing model that survives third-party rate limits and outages, idempotency and replay, and first-class observability per connector.

• A migration path off the current integrations module that doesn't break existing customers - incremental, measurable, reversible.

• The internal developer experience that lets a new integration go from spec to production in days, not quarters - SDKs, contracts, sandboxes, and tests.

• Patterns for API design, versioning, and backward compatibility that the rest of engineering adopts.

Must-haves

• You've built platforms or developer-facing systems that other engineers built on top of - not just features.

• Deep experience with distributed systems fundamentals: queues, idempotency, eventual consistency, retries/backoff, webhook delivery, and failure isolation.

• A track record of large-scale migrations done safely, with rollback and zero-downtime cutovers.

Track C - Core Systems & Scale Principal Engineer

Your charter. Take the core JustCall platform - the PHP monolith and the Node services around it - and turn ten years of accreted complexity into a clean, observable, scalable foundation, without stopping the business.

What you'll own in your first 6–12 months

• A decomposition strategy for the monolith: where to carve services, where to leave the monolith, and a strangler-fig plan that ships value every sprint.

• Reliability and performance wins on the hottest paths - p99 latency, database hotspots (MySQL/MongoDB), and the noisy-neighbor problems that come with a shared monolith.

• A migration of legacy surfaces (e.g., PHP > modern services / front-end) with safety nets: feature flags, shadow traffic, automated regression, and clean rollback.

• Raising the floor on engineering fundamentals: CI/CD, test strategy, observability (we run CubeAPM), and on-call health.

Must-haves

• You've operated and evolved a large, high-traffic system in production and know what breaks at scale - and how to fix it without a big-bang rewrite.

• Strong instincts for incremental migration and risk management; you've led at least one multi-quarter modernization that actually landed.

• Fluency in the messy middle: profiling, query optimization, caching, queueing, and capacity planning.

What We're Looking For

• Demonstrated scale. You've built or operated systems that mattered, under load, and can talk about the trade-offs in detail.

• Range. Legacy and greenfield. Depth and breadth. Code and design.

• Judgment about what not to do. The most valuable thing a Principal Engineer does is kill the wrong project early.

• Ownership reflex. When something is broken and unowned, you pick it up.

• Clarity. You can make a hard idea simple in writing and in a room.

About SaaS Labs

JustCall is SaaS Labs' flagship product - used by 6,000+ businesses across 70+ countries to run their customer conversations. We're backed by Peak XV and Base10 Partners, have crossed $40M ARR, and are building toward $100M with the team, the product, and the infrastructure to get there.

If this is the role you've been waiting to find - let's talk.

SaaS Labs takes pride in being an equal opportunity employer. We believe diverse teams build better products, which is why we're committed to making hiring or any employment decision regardless of race, colour, religion, national origin, age, sex, marital status, ancestry, disability, genetic information, veteran status, gender identity, sexual orientation, or any other characteristic.