About the Role

We're looking for an AI Engineer to join the proAgent pod and work on the systems that power our autonomous voice agents in live financial conversations. You'll work alongside a small, high-agency team where you will have real ownership over features and components from day one.

This is a hands-on engineering role. You'll be deep in the code — building agent logic, integrating speech models, tuning prompts, and debugging gnarly real-time issues. You don't need to have done all of this before, but you need to be the kind of engineer who figures things out fast, takes feedback well, and ships.

What You'll Do

Agent Loop & Reasoning

• Build and maintain components of the agentic runtime that powers multi-turn financial conversations — covering payment negotiations, compliance guardrails, and objection handling
• Implement context management logic that tracks consumer state, conversation history, and business rules across long, branching dialogues
• Write and iterate on primitives that balance conversational fluidity with structured reasoning — the agent needs to feel human while making verifiable decisions

Voice AI Systems

• Work on our real-time voice pipeline with a target of 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 (STT, TTS, speech-to-speech) — we currently work with ElevenLabs and Cartesia for TTS, and Deepgram for STT, and are always exploring what's next
• Debug streaming audio and WebRTC issues in production

LLM Infrastructure

• Write and refine prompts, implement orchestration flows, and contribute to model routing logic
• Build components of our evaluation framework — helping measure agent quality across conversation quality, empathy, and compliance adherence
• Stay curious about new models and tools — flag opportunities and contribute to build-vs-integrate discussions

What You Bring

• 2 – 5 years of hands-on engineering experience, with good exposure to building or working with ML or AI systems in production.
• Solid Python fundamentals — you are comfortable writing clean, maintainable code and debugging production issues.
• Some experience working with LLMs: prompt engineering, API integrations, or building simple pipelines or agents.
• High bias for action — you don't wait to be told exactly what to do, and you push yourself to ship rather than over-engineer.
• Strong fundamentals in Python; familiarity with TypeScript is a plus.
• Eager to learn in a fast-moving environment, take ownership of your work, and ask good questions.

Even Better

• Exposure to voice AI: speech recognition, synthesis, or telephony systems — even if only through personal projects or coursework
• Any background or interest in fintech, lending, or collections
• You've tinkered with Twilio, LiveKit, ElevenLabs, or similar real-time infrastructure
• You've built a small agentic system — even a side project — that combines LLM reasoning with structured actions
• Familiarity with streaming protocols, WebRTC, or low-latency system design

Why This Role

• Real ownership from day one: proAgent is a small pod. You won't be a cog — 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.

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 engieering 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.