Sr. Machine Learning Engineer

Build low-latency voice and conversational AI agent pipelines at AppFolio, supporting real-time, multi-channel customer interactions within Realm-X. This onsite role in Columbus, OH pairs agent systems with streaming infrastructure to help deliver experiences where quality, evaluation, and reliability matter.

What you’ll do

• Architect and ship voice and text agent pipelines for real-time, multi-turn customer conversations.
• Make principled trade-offs between reasoning depth and latency across frontier LLMs, smaller models, and routing strategies.
• Lead a small pod of ML and platform engineers, raising the bar on agent evaluation, observability, and incident response.
• Work closely with Product and Voice channel teams to define KPIs, eval harnesses, and acceptance criteria for agent quality.
• Drive selective SLM fine-tuning and inference optimization to improve voice latency and cost.

What you bring

• Deep, shipped experience with LangChain, LangGraph, LangSmith, and LangChain Deep Agents (or equivalent agent frameworks).
• Hands-on experience with Voice-to-Voice models and traditional TTS / STT pipelines, including understanding trade-offs between end-to-end voice models and modular STT-then-LLM-TTS architectures.
• Strong grasp of LLM reasoning behavior, tool use, structured output, and reasoning-vs-latency trade-offs across providers.
• Production experience with Twilio (or comparable telephony) and AWS.
• Expert Python, async programming, and WebSockets for real-time, bidirectional streaming.
• Solid foundation in deep learning, model evaluation, and inference optimization, including the ability to deploy with Docker on AWS.
• Demonstrated ability to lead a small team, mentor engineers, and partner credibly with Product and Design.
• Shipped production AI agents serving real users in voice and/or text channels.
• Think in pipelines and systems, move fast with sound engineering judgment, and collaborate with humility and low-ego.
• Value work-life balance as a foundation for sustained high performance.

Nice to have

• 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 GitHub, in open-source agent frameworks, or in community competitions.

Compensation & benefits

• Base pay range: USD 167,200 - 209,000 per year.
• The listed compensation range does not include additional benefits or any discretionary bonuses that may apply based on role and/or employment type.
• Regular full-time employees are eligible for benefits.
• Final compensation is determined by factors including skills, education, experience, and internal equity.

Location: Find out more about AppFolio locations by visiting their site. All late-stage candidates complete an in-person meeting with an AppFolian as part of the hiring process. #LI-KB1

Technologies: LangChain, LangGraph, LangSmith, LangChain Deep Agents, Voice-to-Voice models, TTS, STT, Twilio, AWS, Python, WebSockets, Docker