SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Prodigal is building AI agents for loan servicing and collections, founded in 2018 by IIT Bombay alumni. The company has grown to 100+ enterprise customers across North America and is backed by Y Combinator, Accel, and Menlo Ventures. They position themselves as the fastest-growing AI company in consumer finance.
You'll join the proAgent team as an Applied AI Engineer, working on autonomous voice agents that conduct live financial conversations. This is a hands-on role where you'll own features and components from day one, working alongside a small, high-agency team.
Key responsibilities include:
**Agent Loop & Reasoning**: Build and maintain the agentic runtime powering multi-turn financial conversations covering payment negotiations, compliance guardrails, and objection handling. Implement context management logic tracking consumer state, conversation history, and business rules across long dialogues. Write primitives balancing conversational fluidity with structured reasoning.
**Voice AI Systems**: Work on real-time voice pipelines targeting sub-1 second latency across transcription, reasoning, and synthesis. Contribute to VAD tuning and turn-taking logic for natural conversations. Evaluate and integrate speech models (currently using ElevenLabs and Cartesia for TTS, Deepgram for STT). Debug streaming audio and WebRTC issues in production.
**LLM Infrastructure**: Write and refine prompts, implement orchestration flows, and contribute to model routing logic. Build evaluation framework components measuring agent quality across conversation quality, empathy, and compliance. Stay current on new models and tools.
You'll need 2–5 years of hands-on engineering experience with exposure to ML/AI systems in production. Strong Python fundamentals are essential, along with experience working with LLMs (prompt engineering, API integrations, or building simple pipelines/agents). You should have a high bias for action, shipping over over-engineering, and strong ownership mentality.
Bonus experience includes voice AI exposure (speech recognition, synthesis, telephony), fintech/lending/collections background, familiarity with Twilio/LiveKit/ElevenLabs, experience building agentic systems, or knowledge of streaming protocols and WebRTC.
