Sr. Machine Learning Engineer

AppFolio is seeking a Senior Machine Learning Engineer to design and ship voice and conversational AI agents within Realm-X. This role will define production-grade voice and chat agent pipelines, with a focus on balancing LLM reasoning quality against low-latency streaming across multi-channel customer experiences.

Responsibilities

• Architect and deliver voice and text agent pipelines for real-time, multi-turn customer interactions.
• Evaluate and implement principled trade-offs between reasoning depth and latency using frontier LLMs, smaller models, and routing strategies.
• Lead a small pod of ML and platform engineers, strengthening standards for agent evaluation, observability, and incident response.
• Collaborate with Product and Voice channel teams to define KPIs, build evaluation harnesses, and establish agent acceptance criteria focused on quality.
• Drive selective Small Language Model (SLM) fine-tuning and inference optimization to improve voice latency and control cost.

Requirements

• Deep, production experience with LangChain, LangGraph, LangSmith, and LangChain Deep Agents (or equivalent agent frameworks).
• Hands-on experience with voice systems, including Voice-to-Voice models and traditional TTS/STT pipelines, with clear understanding of end-to-end voice models versus modular STT LLM TTS architectures.
• Strong knowledge of LLM reasoning behavior, tool use, structured output, and reasoning-versus-latency trade-offs across model providers.
• Production experience with Twilio (or comparable telephony) and AWS.
• Expertise in Python, async programming, and WebSockets to support real-time, bidirectional streaming.
• Solid foundation in deep learning, model evaluation, and inference optimization, including the ability to deploy with Docker on AWS.
• Proven ability to lead a small team, mentor engineers, and partner credibly with Product and Design.
• Demonstrated experience shipping production AI agents serving real users in voice and/or text channels.
• Systems thinking, with the ability to reason about pipelines and end-to-end behavior beyond model development.
• Ability to move quickly while maintaining sound engineering judgment.
• Collaborative, low-ego working style, focused on elevating teammates.
• Values work-life balance as a foundation for sustained high performance.

Technologies

• LangChain, LangGraph, LangSmith, LangChain Deep Agents
• Voice-to-Voice models, TTS, STT
• Twilio, AWS
• Python, async programming, WebSockets
• Docker
• LLM, Small Language Model (SLM)
• RAG

Benefits

• Regular full-time employees are eligible for benefits
• #LI-KB1

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.

Location

Atlanta, GA (onsite)

Find out more about our locations by visiting our site.

Compensation & Benefits

• The compensation that we reasonably expect to pay for this role is USD 167,200 - 209,000 base pay.
• The actual compensation will be determined by factors including skills, education, experience, and internal equity.
• Compensation is one component of a comprehensive Total Rewards package.
• The compensation range does not include additional benefits or any discretionary bonuses that may be available based on role and/or employment type.

Regular full-time employees are eligible for benefits - see here.