AppFolio
AppFolioVerified Source

Senior Machine Learning Engineer, Voice & Conversational AI

167K–209K
Onsite · San Diego, California
Posted August 12, 2026
payroll

Overview

You will lead the development of Realm-X's voice and text AI agent pipelines, serving real-time, multi-turn interactions for AppFolio's property management platform. You will architect systems that balance LLM reasoning depth with latency, driving production agents that handle millions of customer conversations. As a technical lead, you'll guide a small pod of engineers, define quality metrics, and collaborate with Product and Voice teams. This role uniquely combines deep LLM agent frameworks, Twilio telephony, and AWS streaming, placing you at the core of AI-native property management transformation. We're looking for a senior engineer with a track record of shipping production agents, strong Python expertise, and a pragmatic mindset for real-world performance.

What You'll Do8

  • 1Architect and ship LangGraph-based voice and text agent pipelines that manage real-time, multi-turn customer interactions.
  • 2Optimize reasoning-vs-latency trade-offs across frontier LLMs, smaller models, and routing strategies to deliver sub-second response times.
  • 3Lead a small pod of ML and platform engineers, setting the bar for agent evaluation, observability, and incident response.
  • 4Define agent quality KPIs and acceptance criteria in partnership with Product and Voice teams.
  • 5Drive selective SLM fine-tuning and inference optimization for voice latency and cost.
  • 6Build and deploy Docker containers on AWS for scalable, reliable agent infrastructure.
  • 7Integrate Twilio telephony and WebSockets for bidirectional, low-latency voice and text streaming.
  • 8Establish robust evaluation harnesses using LangSmith to continuously measure and improve agent performance.

Requirements8

  • 15+ years building production AI agents for voice or text channels.
  • 2Deep LangChain, LangGraph, LangSmith, and agent framework experience.
  • 3Hands-on with voice-to-voice models and TTS/STT pipelines, understanding modular vs. end-to-end trade-offs.
  • 4Strong grasp of LLM reasoning, tool use, structured output, and latency trade-offs.
  • 5Production experience with Twilio and AWS for telephony and cloud services.
  • 6Expert Python with async programming and WebSockets for real-time streaming.
  • 7Solid ML fundamentals in deep learning, model evaluation, and inference optimization.
  • 8Demonstrated leadership of small teams and mentoring engineers.

Salary Insight

$167 - $209k per year

Location

Typeonsite
LocationSan Diego, California

Required Skills

LangChainLangGraphLangSmithVoice-to-Voice modelsTTSSTTTwilioAWSPython
Share:

Similar open positions

Explore active roles that match your skills and interests.

AppFolio

AppFolio

22h agoDenver, Coloradopayroll

Senior Machine Learning Engineer, Voice AI Agents

You will own the design and deployment of voice and text AI agents within Realm-X, AppFolio's AI-native platform for real estate. You'll lead a small pod of engineers to ship real-time, multi-turn conversational experiences that handle millions of interactions across our customer base. Working with Product, Voice channel, and ML Platform teams, you'll translate cutting-edge agent research into reliable, low-latency pipelines. This role is for engineers who think in systems, not just models, and value pragmatic trade-offs between reasoning depth and latency. You'll be part of a collaborative, low-ego culture that prioritizes work-life balance as a foundation for sustained high performance.

167K–209K
LangChainLangGraphLangSmith+9 more
AppFolio

AppFolio

1d agoSan Francisco, Californiapayroll

Senior Machine Learning Engineer AppFolio

Design and ship next generation voice and conversational AI agents within Realm-X. Define production voice and chat agent pipelines at intersection of LLM agent frameworks, real-time voice technology, and streaming infrastructure. Work with Product Voice channel and ML Platform teams to translate cutting-edge agent research into reliable low-latency multi-channel experiences.

167K–209K
LangChainLangGraphLangSmith+8 more
AppFolio

AppFolio

1d agoWashington, District of Columbiapayroll

Senior Machine Learning Engineer AppFolio

Design and ship next generation voice and conversational AI agents within Realm-X. Define production voice and chat agent pipelines while collaborating with Product Voice and ML Platform teams. Translate cutting edge agent research into reliable low latency multi channel experiences.

167K–209K
LangChainLangGraphLangSmith+2 more
AppFolio

AppFolio

1d agoChicago, Illinoispayroll

Senior Machine Learning Engineer AppFolio Chicago

Design and ship next generation voice and conversational AI agents within Realm-X. Define production voice and chat agent pipelines. Work at intersection of LLM agent frameworks real-time voice technology and streaming infrastructure. Collaborate with Product Voice channel and ML Platform teams to translate research into reliable low-latency multi-channel experiences.

167K–209K
LangChainLangGraphLangSmith+7 more
S Linx LLC

S Linx LLC

23h agoDenver, Coloradopayroll

Senior AI Engineer, NLP & LLM

Senior AI Engineer owns design and deployment of production AI systems for customer interaction analytics at S Linx LLC. You build on NLP and LLM technologies to process call transcripts and drive real-time agent assist. The role sits within a cross-functional team of data scientists and engineers. You own the full lifecycle from model training to deployment. This position requires deep machine learning expertise and a bias for shipping.

125K–135K
AI/ML leadershipMachine LearningDeep Learning+4 more

David Joseph & Company

22h agoSan Francisco, Californiapayroll

Voice AI Infrastructure Engineer

You will architect and build the simulation, observability, and evaluation layer for Voice AI agents, serving millions of calls monthly for enterprise clients across banking, healthcare, and food service. You'll design resilient AWS infrastructure for real-time conversations and own technical execution end to end. As part of a ~10-person team, you'll work directly with customers to deploy the product. This role stands out for its full ownership and the complexity of real-time voice AI.

225K–300K
pythonawsfastapi+2 more