AI Engineer

Role Overview

You'll build and optimize the AI systems behind our platform - starting with the real-time conversational engine behind Joy, and extending across the surfaces that surround it: call summarization and analytics, multi-modal orchestration, document intelligence, and computer-use agents. This is a hands-on engineering role at the intersection of applied LLMs, real-time audio, and agentic workflows.

Responsibilities

• Build and optimize Joy's real-time voice pipeline (streaming STT → LLM → TTS) on a voice AI orchestration framework.
• Implement and tune latency techniques: sentence-chunked streaming TTS, speculative tool prefetching, filler speech, parallel tool execution, and prompt caching.
• Integrate LLMs for conversational turns - function/tool calling, prompt engineering, structured outputs, and grounded responses.
• Develop and improve the RAG layer over vector search: retrieval quality, knowledge-base grounding, and refusal behavior.
• Benchmark models across multiple frontier LLM providers on latency, cost, and quality.
• Build and maintain evaluation harnesses covering retrieval metrics and generation metrics.
• Integrate telephony and messaging (SIP trunking / SMS) and coordinate with EHR middleware.
• Build call summarization that turns raw transcripts into structured post-call notes.
• Contribute to the orchestration layer that coordinates AI across modalities (voice, SMS, document).
• Build the document intelligence pipeline for healthcare benefits-verification documents.
• Develop computer-use / browser agents that operate EHR portals and web workflows.
• Deploy, monitor, and tune services on a serverless container platform.
• Own the AI/ML technical vision and roadmap across the full agent portfolio.
• Lead, mentor, and grow the AI engineering team.
• Set the end-to-end architecture for the voice pipeline and orchestration layer.
• Define and drive service-level objectives per surface.
• Own model strategy: build-vs-buy decisions, provider and region selection.
• Establish the evaluation and quality framework.

Requirements

• 2–5 years building production software, with meaningful applied LLM / ML work.
• Strong Python, including async and modern async web frameworks.
• Hands-on experience with LLM applications: prompting, tool/function calling, RAG, embeddings, and vector databases.
• Solid grasp of real-time or streaming systems and the discipline to reason about latency budgets.
• Comfort with cloud infrastructure (GCP) and containerized deployment.
• Agentic / computer-use experience - browser or desktop automation, tool-using agents, multi-step task orchestration.
• Streaming STT / TTS systems.
• LLM / RAG evaluation tooling and frameworks.
• A data-driven, benchmark-first instinct.

Skills

• Python
• LLM
• RAG
• GCP
• STT/TTS

Nice to Have

• Voice / telephony experience: SIP