Senior ML Engineer: Real-Time Voice Agent Pipelines

AppFolio; Denver (CO); On-site; USD 167,000 - 209,000; Full time

Job summary

AppFolio is hiring a Senior Machine Learning Engineer to design and ship next-gen voice and conversational AI agents within Realm-X. You will help define production voice and chat agent pipelines, collaborating across Product, Voice, and ML Platform teams to deliver reliable, low-latency experiences at scale.

You’ll lead a small pod of ML and platform engineers, focusing on agent evaluation, observability, and incident response, while driving QoS through KPI-driven testing and optimized

Qualifications

• Shipped production AI agents for voice/text channels.
• Think in pipelines and systems, not just models.
• Demonstrated fast delivery with sound engineering judgment.
• Humility, collaboration, and leadership to elevate teammates.
• Commitment to work-life balance to sustain high performance.

Responsibilities

• Ship voice and text agent pipelines for real-time interactions.
• Balance reasoning depth with latency across LLMs and models.
• Lead a pod of ML and platform engineers; improve observability and incident response.
• Define KPIs, eval harnesses, and acceptance criteria for agent quality.
• Optimize for voice latency and cost with selective fine-tuning of SLMS.

Skills

Agent frameworks

Voice stack

LLM fluency

Telephony & cloud

Python

WebSockets

Docker on AWS

Leadership

Tools

LangChain

LangGraph

LangSmith

LangChain Deep Agents

Twilio

AWS

Python

Job description

AppFolio is hiring a Senior Machine Learning Engineer to design and ship next-gen voice and conversational AI agents within Realm-X. You will help define production voice and chat agent pipelines, collaborating across Product, Voice, and ML Platform teams to deliver reliable, low-latency experiences at scale.

You’ll lead a small pod of ML and platform engineers, focusing on agent evaluation, observability, and incident response, while driving QoS through KPI-driven testing and optimized