At Prodigal, we are building AI Agents for loan servicing and collections. Founded in 2018 by IITB alumni, our journey began with one bold mission: to eradicate the inefficiencies and confusion that have plagued the lending and collections industry for decades. We are backed by Y Combinator, Accel and Menlo Ventures.
Today, we stand at the forefront of a seismic shift in the industry, building Agentic AI applications for consumer finance. Powered by our cutting-edge platform, Prodigal’s Intelligence Engine (PIE), we’re creating the next-generation agentic workforce - one that empowers companies to achieve unprecedented levels of operational excellence and intelligence.
With over half a billion consumer finance interactions processed and a growing impact on more than 100 leading companies across North America, we’ve established ourselves as the go-to partner for organizations that demand more from their AI solutions. Our unparalleled experience, coupled with our trusted customer relationships, uniquely positions us to build Agentic AI applications that will revolutionize the future of consumer finance.
At Prodigal, we are driven by a singular, unrelenting purpose: to transform how consumer finance companies engage with their customers and, in turn, drive successful outcomes for all.
About the Role
We're looking for a Tech Lead to own the technical direction of proAgent's core architecture. You'll lead a small, high-agency team building AI Agents that handle nuanced financial conversations-where every millisecond of latency and every reasoning decision matters.
This is a player-coach role. You'll write code, make architectural decisions, and set the technical bar for how we build intelligent, low-latency voice agents.
What You'll OwnAgent Loop & Reasoning- Design the agentic runtime that powers natural, multi-turn conversations while executing complex business logic (payment negotiations, compliance guardrails, objection handling)
- Build primitives that balance conversational fluidity with structured reasoning-the agent needs to feel human while making verifiable decisions
- Create context management systems that track consumer state, conversation history, and business rules across long, branching dialogues
- Architect our real-time voice pipeline for sub-1s latency across transcription, reasoning, and synthesis
- Own VAD tuning, and turn-taking logic that makes conversations feel natural
- Evaluate and integrate speech models (STT, TTS, speech-to-speech) as the landscape evolves-we currently work with ElevenLabs and Cartesia for Text to Speech, and Deepgram for Speech to Text, and are always exploring what's next
- Debug and optimize streaming audio and WebRTC
- Design our prompting, orchestration, and model routing strategies
- Build evaluation frameworks that measure agent quality beyond accuracy-conversation quality, empathy, compliance adherence
- Stay current on model capabilities and make pragmatic build-vs-integrate decisions
- Set architectural direction for proAgent platform and surrounding applications
- Mentor engineers and establish engineering practices that scale
- Partner with Product and Client teams to translate customer problems into technical roadmaps
- Make tradeoffs between shipping fast and building durable systems-we need both
- 4+ years building production systems, with 1+ years in a Lead for a project
- Hands-on work with LLMs in production: prompt engineering, orchestration, evaluation
- High bias for action to see things to production - real-time systems can get gnarly, and truly high bias is needed to take things to production
- Strong fundamentals in Python and TypeScript
- Clear technical communication-you can explain complex tradeoffs to engineers and stakeholders alike
- Experience with voice AI: speech recognition, synthesis, telephony systems
- Background in fintech, lending, or collections
- Experience with Twilio, LiveKit, ElevenLabs, or similar real-time infrastructure
- You've built agentic systems that combine LLM reasoning with structured actions
- Track record of building and scaling small teams
- High leverage: proAgent is poised to handle millions of live consumer conversations every day. Your architectural decisions directly impact business outcomes.
- Frontier work: Voice AI that reasons, decides, and acts is one of the hardest problems in applied AI. We're building it.
- Ownership: Small team, big scope. You'll shape what proAgent becomes.
From day 1, Prodigal has been defined by talented, humble, and hungry leaders and we want this mindset and culture to continue to blossom from top to bottom in the company. If you have an entrepreneurial spirit and want to work in a fast-paced, intellectually-stimulating environment where you will be pushed to grow, then please reach out because we are looking to build a transformational company that reinvents one of the biggest industries in the US.
To learn more about us - please visit the following:
Our Story - https://www.prodigaltech.com/our-story
What shapes our thinking - https://link.prodigaltech.com/our-thesis
Our website - https://www.prodigaltech.com/
Top Skills
What We Do
Prodigal is a pioneer of Collection & Servicing Intelligence, a new category of AI software, which enables banks, lenders and collection agencies of all sizes to quickly and efficiently collect accounts receivables. Our cloud-native, Collection & Servicing Intelligence platform delivers actionable insights for banks, lenders, and ARM agencies to maximize revenue, optimize operations, and minimize compliance risk.
Prodigal delivers artificial intelligence and machine learning capabilities to lenders and ARM agencies. Prodigal restores value from accounts past due and improves servicing productivity while retaining customer loyalty. We empower entire teams from executive leadership to representatives with data and insights needed to segment and prioritize accounts, to enhance portfolio yield, and to address procedural and legal (TCPA, FDCPA, UDAAP, ...) non-compliance.
With our Collection & Servicing Intelligence Platform, senior executives have complete intelligence about expected liquidation, aggregated agent productivity, and FDCPA/TCPA non-compliance in real-time — an imperative for a modern collections business in an increasingly regulated environment.
Prodigal is headquartered in the heart of Silicon Valley (Sunnyvale, CA) and is founded by industry veterans with deep expertise in financial services, predictive modeling, speech AI and core engineering.
Our investors include top tier investors like Menlo Ventures, Accel andY Combinator. Prodigal has been featured in TechCrunch, American Banker, CBS News, Fortune, insideARM and other leading technology and financial services news sites.
