About the Role
We're looking for an AI Lead to own the technical direction and team behind proAgent's core intelligence. You'll lead a small, high-agency pod building AI Agents that handle nuanced financial conversations — where every millisecond of latency, every reasoning decision, and every team member's growth matters.
This is a player-coach role with full pod accountability. You'll write code, define the AI architecture, set the technical bar, and directly manage and grow a team of AI engineers. The right person has been in the weeds of voice AI and LLM systems long enough to have strong opinions — and has led teams long enough to know how to bring others along.
What You'll Own
Pod Leadership & Team Building
- Lead and grow the proAgent AI pod — hiring, mentoring, and developing a team of AI engineers who own everything from agent reasoning to voice pipeline optimization.
- Set the technical bar for AI engineering at Prodigal: what rigorous experimentation looks like, what production-readiness means, and how the team should make build-vs-integrate decisions.
- Run sprint cycles, technical reviews, and roadmap planning — keep the pod shipping fast without losing architectural coherence.
- Work directly with the CTO and product leadership to translate company priorities into a pod-level AI roadmap with clear milestones and ownership.
Agent Loop & Reasoning
- Own the architectural direction of the agentic runtime that powers natural, multi-turn conversations while executing complex business logic — payment negotiations, compliance guardrails, objection handling.
- Set the design standards for primitives that balance conversational fluidity with structured reasoning: the agent needs to feel human while making verifiable decisions.
- Define how the pod builds context management systems that track consumer state, conversation history, and business rules across long, branching dialogues.
- Drive the evolution of agent reasoning as model capabilities and product requirements grow — stay ahead of what's possible and what the business needs.
Voice AI Systems
- Own the technical strategy for our real-time voice pipeline — sub-1s latency across transcription, reasoning, and synthesis is a hard requirement, not a goal.
- Set the direction for VAD tuning, turn-taking logic, and the standards that make conversations feel natural at scale.
- Lead evaluation and integration decisions for speech models (STT, TTS, speech-to-speech) as the landscape evolves — we currently work with ElevenLabs and Cartesia for TTS, and Deepgram for STT, and are always exploring what's next.
- Establish engineering practices for debugging and optimizing streaming audio and WebRTC across the pod.
LLM Infrastructure
- Own Prodigal's prompting, orchestration, and model routing strategy — set the standards for the pod.
- Lead the design of evaluation frameworks that measure agent quality beyond accuracy: conversation quality, empathy, compliance adherence, and business outcomes.
- Stay current on model capabilities and make pragmatic build-vs-integrate decisions that balance shipping speed with long-term architectural health.
- Institute red-teaming, adversarial testing, and behavioral evaluation practices before changes reach production.
What You Bring
- 7+ years building production grade engineering systems, with 2+ years leading an AI engineering team or pod with direct reports.
- Proven track record of owning AI product outcomes end-to-end — from problem definition and architecture through production and iteration.
- Hands-on experience with LLMs in production: prompt engineering, orchestration, evaluation, and fine-tuning.
- High bias for action — real-time systems get gnarly fast, and you have a track record of pushing things to production rather than perfecting in isolation.
- Strong fundamentals in Python and TypeScript.
- Demonstrated ability to hire and grow strong AI engineers — you know what great looks like and can develop people toward it.
- Clear technical communication — you can explain complex tradeoffs and system behavior to engineers, product managers, and client stakeholders alike.
Even Better
- Deep experience with voice AI: speech recognition, synthesis, telephony systems, and the real-time constraints that come with them.
- Background in fintech, lending, or collections.
- Hands-on experience with Twilio, LiveKit, ElevenLabs, or similar real-time infrastructure.
- You've designed and shipped agentic systems that combine LLM reasoning with structured actions at production scale.
- Track record of building and scaling small, high-performing AI teams from the ground up.
- Experience in instituting evaluation, observability, and red-teaming practices across a team — not just for your own work.
Why This Role
- High leverage: proAgent is poised to handle millions of live consumer conversations every day. Your architectural decisions and the team you build directly determine business outcomes.
- Frontier work: voice AI that reasons, decides, and acts is one of the hardest problems in applied AI — add compliance, empathy, and financial stakes, and it gets harder. We're building it.
- Real ownership: small pod, big scope, full accountability. You will shape what proAgent's intelligence becomes, and the team that builds it.
- Executive partnership: You will work directly with the CTO and the founding leadership. The decisions you make in this role will define Prodigal's AI strategy for years.