Company
Prodigal Technologies
Founded in 2018 by IIT Bombay alumni, Prodigal builds Agentic AI applications for consumer finance — loan servicing, collections, account resolution — powered by the Prodigal Intelligence Engine (PIE), which unifies CRM, dialer, and conversation data into hyper-personalized treatment recommendations at scale.
Who You'll Work With
Meet the Applied AI team.
The small, high-agency pod you'd be shipping alongside.
The Problem
Why voice AI changes everything in finance.
proAgent
The voice AI pipeline you'll work inside.
Target: sub-1s end-to-end latency
Real-Time Infra
Custom pipeline · VAD tuning · Turn-taking logic · WebRTC
Speech Layer
STT · ElevenLabs + Cartesia TTS · Speech-to-speech eval
LLM Orchestration
Prompt engineering · Model routing · Agentic runtime
Intelligence (PIE)
CRM + dialer + conversation data merged · Context injection
What You'll Do
Three areas. Hands-on from week one.
You don't need to have done all of this before — you need to be the kind of engineer who figures things out fast, takes feedback well, and ships.
Agent Loop & Reasoning
Build and maintain components of the agentic runtime and agent harness powering multi-turn financial conversations — payment negotiations, compliance guardrails, objection handling
Implement context management that tracks consumer state, conversation history, and business rules across long, branching dialogues
Write primitives that balance conversational fluidity with structured reasoning — the agent has to feel human while making verifiable decisions
Voice AI Systems
Work on our real-time voice pipeline, targeting sub-1s latency across transcription, reasoning, and synthesis
Contribute to VAD tuning and turn-taking logic that makes conversations feel natural
Help evaluate and integrate speech models — we currently work with ElevenLabs and Cartesia for TTS, and a leading STT provider
Debug streaming audio and WebRTC issues in production
LLM Infrastructure
Write and refine prompts, implement orchestration flows, contribute to model routing logic
Build components of our evaluation framework — measuring conversation quality, empathy, and compliance adherence
Stay curious about new models and tools, and weigh in on build-vs-integrate calls
Ideal Engineer
What we're looking for.
You Bring
Even Better
Why This Role
Why this matters now.
Real Ownership From Day One
The Applied AI team behind proAgent is small in size, high in talent density. You'll own components, ship features, and see your work in live consumer conversations within weeks.
Frontier Work
Voice AI that reasons, decides, and acts is one of the hardest problems in applied AI. You'll be learning by doing on problems most engineers never touch.
Strong Mentorship
You'll work directly with senior engineers and the AI Lead, who will invest in your growth — this is a place to level up fast.
High-Leverage, Early Career
The decisions you make and the code you write will impact millions of financial conversations. Rare for an early-career role.
What To Expect
The interview process.
We run fast, short cycles — either all rounds in a single day, or one round a day to close within a week. Every round is eliminatory and you'll get feedback within 15 minutes.
In The News
Prodigal in the news.
A few places we've been covered recently.
Can this AI agent redefine debt collection?
FirstSource's collections lead now rates the AI above 80–90% of his own human agents — and says it never gets tired.
The Ship of Theseus Moment for AI
A long-read on how AI is reshaping company identity — featuring perspectives from Prodigal's founders.
Revolutionizing Debt Collection: Prodigal's AI Empathy in Financial Recovery
A profile on how Prodigal is building empathy into AI-driven debt collection and financial recovery.
Go Deeper
Explore what we've built.
High leverage.
Frontier work.
Real ownership.
A small, high-density, high-agency Applied AI team. No layers, no gatekeeping — mentorship from senior engineers and the AI Lead, and your code in live conversations within weeks.