Staff Software Engineer - AI Engineering

Contact: Feel free to connect with https://www.linkedin.com/in/gchambers/ Staff Software Engineer, AI Engineering About the Company A well-funded health tech unicorn building the full operating system for independent medical practices across the US. The platform serves over 140,000 providers and covers the complete practice lifecycle — clinical infrastructure, billing, compliance, revenue cycle management, and patient acquisition. A significant portion of recent funding is mandated for a root-to-branch AI transformation across the entire product and business. The engineering culture is senior, stable, and high-retention — average tenure on the team is six to seven years. The Role The Revenue Cycle Management team is seeking a Staff Software Engineer to lead the hands-on implementation, design, and adoption of AI agents and AI-native capabilities across their billing and revenue cycle platform. This role combines deep software engineering expertise with direct experience building production AI systems. You will help transform how healthcare organizations manage billing, payments, claims, and operational workflows by applying Large Language Models, intelligent automation, retrieval systems, and agentic AI architectures to solve real-world business problems. As a senior individual contributor, you will operate at the intersection of platform architecture, AI systems engineering, and business transformation. You will influence technical strategy across teams, implement reusable AI capabilities, and establish engineering standards for building reliable, secure, and scalable AI-powered systems. An important note on language: Much of the hands-on AI agent implementation is expected to use Python and frameworks such as LangChain or LangGraph. Because the team's day-to-day platform work includes Java and Spring Boot, the successful candidate must also be comfortable contributing to Java codebases, reviewing Java code, and mentoring engineers who work primarily in Java. Mastery of both languages is not required - expert-level depth in either Python or Java, combined with working proficiency in the other, is the bar. What You'll Work On Own hands-on implementation of production AI agents and agentic workflows, with particular emphasis on Python-based stacks such as LangChain and LangGraphDesign, develop, test, and operate AI-enabled services that combine agent orchestration, application logic, APIs, retrieval, and AI models for real customer and operational use casesConnect Python-based AI agents and services with Java/Spring Boot platform services through well-defined APIs, events, and contracts; contribute in both ecosystems as neededIntegrate LLMs, ML models, enterprise data sources, and external AI services using strong engineering patterns for reliability, observability, maintainability, and securityBuild bounded, auditable AI workflows with clear fallback behavior, evaluation, authorization boundaries, and human review where appropriatePartner with product, design, data, and operational teams to turn workflow pain points into scalable software solutions with measurable impactConduct thorough code reviews across AI services and Java/Spring Boot codebases; mentor junior and mid-level engineers including those whose primary work is in JavaIdentify bottlenecks and improve latency, throughput, quality, and cost across AI agent workflows and backend service layersEvaluate emerging AI engineering practices and adopt them when they improve product quality or delivery speed What We're Looking For 8+ years of professional software engineering experience building scalable distributed systemsExpert-level depth in Python or Java, with working proficiency in the other; comfort reading, writing, and reviewing Java code and mentoring Java engineers is required regardless of primary language2-3+ years of hands-on experience designing, shipping, and maintaining production AI-enabled applications combining LLMs, core application logic, and business workflowsPractical experience with AI orchestration frameworks — LangGraph, LangChain, LlamaIndex, or CrewAI — and deep understanding of RAG, tool calling, context and state management, and HITL patternsStrong background in distributed systems, event-driven architectures, asynchronous processing, and messaging platforms such as KafkaDemonstrated experience building multi-step agents that use tools, retrieval, state or memory, structured outputs, and explicit control flow — able to explain design decisions and production tradeoffsProven experience implementing production AI safeguards: real-time observability, latency and cost monitoring, automated evaluation pipelines, and robust fallback mechanismsCloud-native experience across AWS, Azure, or GCP Preferred Healthcare IT, RCM, billing, claims processing, fintech, or similarly regulated, high-compliance domain backgroundExperience building autonomous multi-step agentic systems with multi-tier memory and recursive reasoningKnowledge graph construction and enterprise vector search architecturePyTorch, HuggingFace Transformers, custom embedding models, or fine-tuning experiencePast experience as a Founding Engineer, Principal Architect, or early-stage platform lead driving org-wide AI/ML adoption Logistics Fully remoteCanada-based candidates with work authorization only — placed through Syndesus as employer of recordBase salary + benefits only; no bonus or equity in current EOR structure — generous salary raises twice yearly in lieu of bonusComprehensive benefits (Sun Life, 100% family coverage) administered through SyndesusUnlimited PTO, 15-day minimum mandate Compensation: $180,000-$220,000 CAD + Benefits Compensation: $180,000-$220,000 CAD + Benefits