Applied AI Engineer

About this role

About the role: - Build and maintain AI and machine learning systems running in production environments - Work with large language models across prompt engineering, API connections, and multi-step agent architectures - Take ownership of projects from concept through deployment, with a focus on shipping working solutions rather than perfectionism - Contribute to a fast-moving team where you identify what needs doing and drive it forward without waiting for direction What you'll work on: - Real-time voice AI applications, potentially involving speech recognition, text-to-speech, or phone system integrations - Infrastructure and systems that handle streaming, WebRTC, or low-latency requirements - Agentic systems that combine LLM reasoning with structured, executable actions - Production debugging and code quality across distributed systems What we're looking for: - 2 to 5 years building or operating ML and AI systems in live environments - Strong Python skills: you write clean, debuggable code and can troubleshoot production issues - Hands-on experience with LLMs in real applications, whether through prompt work, API calls, or pipeline development - Initiative and self-direction; you don't need detailed instructions to make progress - TypeScript familiarity is a bonus - Genuine curiosity and ownership; you ask thoughtful questions and grow quickly in new areas A strong fit might also have: - Personal or professional work with voice AI, speech systems, or telephony - Interest in or background with fintech, lending, or collections products - Familiarity with tools like Twilio, LiveKit, or ElevenLabs for real-time communication - A side project or portfolio piece showing an agentic system in action - Understanding of streaming, WebRTC, or systems designed for minimal latency