Sr. Machine Learning Engineer

Description

Hi, We're App Folio

We're innovators, changemakers, and collaborators. We're more than just a software company — we're building the AI-native platform where the real estate industry comes to do business. We're transforming Property Management; how property managers operate, how residents live, and how intelligence flows across an entire industry.

Realm-X is App Folio's AI-native platform powering this transformation. It enables a new generation of intelligent capabilities across our products, including Realm-X Assistant (copilot), Flows (AI Agentic workflows) and Performers (autonomous AI Agents). Realm-X serves as both a foundation for internal teams to build and scale AI-powered products, and a core layer delivering intelligent, high-impact experiences directly to our customers.

At its core, Realm-X is built on a structured domain ontology and a set of shared business primitives—such as transactions, actions, reports, metrics, and skills that enable AI systems to deeply understand and operate across the full context of property management workflows. This foundation allows us to build context-aware, action-oriented AI systems that go beyond simple assistance to power real automation and decision-making.

We're hiring a Senior Machine Learning Engineer to design and ship the next generation of voice and conversational AI agents within Realm-X. This role helps define App Folio's production voice and chat agent pipelines, working at the intersection of LLM agent frameworks, real-time voice technology, and streaming infrastructure.

You will work with Product, Voice channel, and ML Platform teams to translate cutting-edge agent and voice research into reliable, low-latency, multi-channel experiences that scale across our entire customer base.

• Ship Voice & Text Agents:
  Architect and ship voice and text agent pipelines that handle real-time, multi-turn customer interactions.
• Reasoning vs. Latency:
  Make principled trade-offs between reasoning depth and latency across frontier LLMs, smaller models, and routing strategies.
• Lead a Pod:
  Lead a small pod of ML and platform engineers; raise the bar on agent evaluation, observability, and incident response.
• Define Quality:
  Partner with Product and Voice channel teams to define KPIs, eval harnesses, and acceptance criteria for agent quality.
• Optimize for Voice:
  Drive selective Small Language Model (SLM) fine-tuning and inference optimization for voice latency and cost.

• You have shipped production AI agents serving real users in voice and/or text channels.
• You think in pipelines and systems, not just models.
• You move fast, deliver impact, and maintain sound engineering judgment.
• You are humble, collaborative, and low-ego, and you elevate those around you.
• You value work-life balance as a foundation for sustained high performance.

• Agent frameworks:
  Deep, shipped experience with Lang Chain, Lang Graph, Lang Smith, and Lang Chain Deep Agents (or equivalent agent frameworks).
• Voice stack:
  Hands-on with Voice-to-Voice models and traditional TTS / STT pipelines; understands the trade-offs between end-to-end voice models and modular STT → LLM → TTS architectures.
• LLM fluency:
  Strong grasp of LLM reasoning behavior, tool use, structured output, and reasoning-vs-latency trade-offs across providers.
• Telephony & cloud:
  Production experience with Twilio (or comparable telephony) and AWS.
• Engineering:
  Expert Python, async programming, and Web Sockets for real-time, bidirectional streaming.
• ML fundamentals:
  Solid foundation in deep learning, model evaluation, and inference optimization; able to deploy with Docker on AWS.
• Leadership:
  Demonstrated ability to lead a small team, mentor engineers, and partner credibly with Product and Design.

• Experience fine-tuning Small Language Models for domain-specific voice applications.
• Familiarity with RAG over structured business data and tool-using agents over API surfaces.
• Prior experience in regulated or customer-facing industries with strict reliability requirements.
• Publicly verifiable work on Git Hub, in open-source agent frameworks, or in community competitions.

Find…