2025 · Airbase Technologies

Airbase — Autonomous AI Interviewer

The AI that interviews every candidate over video and phone, scores them against your rubric, and hands you a ranked shortlist.

TypeScriptBunPythonLLM orchestrationPostgreSQLRedisWebSockets

The role

CTO & Co-Founder — architecture & full build

Highlights

  • Built a real-time voice agent that autonomously conducts video and phone interviews, replacing first-round human screening.
  • Built an in-app AI assistant that runs real tasks on command — operating the app through its own API as the logged-in user.
  • Engineered LLM scoring pipelines that evaluate interviews and applications against rubrics with structured, evidence-backed decisions.
  • Built an AI document pipeline that cut per-document processing cost by ~99%.
  • Designed model-agnostic orchestration with automatic provider fallback — every model swappable, the system stays reliable.
Airbase

// inside_the_product

What Airbase does — and what I built

listening

SageWalk me through a system you scaled.

“Sure — we moved to an event-driven…”

rubric score8.6/10

AI Interviews

Structured first-round interviews, on autopilot

A real-time voice agent interviews every candidate over web or phone — asking your questions, following up naturally, and scoring as it goes. I built the sub-second voice pipeline behind it.

AK94
MR88
JL79

Resume Screening

A ranked shortlist before you open a resume

Every application is read against your rubric and scored, so the strongest matches surface on their own — powered by an LLM scoring pipeline that returns structured, evidence-backed decisions, not vibes.

senior backend · remote3,410 applied
SP92%fit
DN86%fit
RK78%fit

Talent Matching

Rediscover talent you already have

Search everyone who has ever applied and rank them by fit for a new role — vector search across your whole candidate history. Your next hire may already be a yes.

Voice
Video
Text
Email
5+ langsENESFRDEIT

Omnichannel

Meet candidates where they are

Interviews by voice, video, text, or email, in 5+ languages, so you reach your whole audience and far fewer people drop off. One agent across every channel, bridged over WebSockets and Twilio.

// architecture

The system at a high level

A high-level view of the system — a TypeScript/Bun core with AI agents embedded across the product, model-agnostic and driven entirely through APIs.

  1. 01

    Clients

    ReactWebSocketsService Worker

    Recruiter and applicant apps, plus a real-time interview client with client-side recording that survives flaky networks.

  2. 02

    API & services

    BunRESTBullMQ

    A core ATS API with a set of focused services around it — recording, async processing, and the interview bridge — each doing one job.

  3. 03

    Agent & LLM layer

    agentsideTool-useMulti-provider

    A provider-agnostic agent engine (open-sourced as agentside) that drives the app through its own API, plus scoring pipelines that grade against rubrics with structured output.

  4. 04

    Voice pipeline

    STT / TTS / VADTwilio

    A sub-second speech-to-text → LLM → text-to-speech loop that bridges browser and phone callers into one interviewer.

  5. 05

    Data & infrastructure

    PostgreSQLRedisS3Vector search

    Relational data for the ATS, a cache and queue layer, object storage for recordings, and vector search for talent matching.

What it is

Airbase is an autonomous AI interviewer. It runs a structured first-round interview with every candidate — over web or phone — asks the questions you define, follows up naturally, scores against your rubric, and hands you a ranked shortlist. It's the interview-focused edition of Cuee, the full hiring platform, built on the same codebase.

I'm the sole technical founder. I designed the architecture and built the whole system largely solo across TypeScript, Bun, and Python, with AI agents embedded across the product.

The hard parts

  • A voice agent that conducts interviews. Real-time, over web and phone — it listens, asks, follows up, and scores, on its own.
  • An assistant that acts, not chats. It runs real tasks by driving the app through its own API, as the logged-in user, inside their permissions.
  • Decisions you can audit. LLM scoring pipelines grade against rubrics and return structured, evidence-backed output — not vibes.
  • Cost engineered. A document pipeline that cut per-document cost by ~99%.
  • Never locked to one model. Model-agnostic orchestration with automatic provider fallback.

Want something like this built?

~/work/airbase-hiring-platform$