Applied AI Engineer

Accuity

1d•Remote

About The Position

The Applied AI Engineer designs, prototypes, and builds production applications and features that apply existing AI models and services to clinical documentation and revenue cycle workflows. Reporting to the Vice President, Data Science and AI, this role owns the application layer, including user experience, service integration, prompt design, safeguards, testing, and production performance. The engineer partners with AI Engineering, Data Science, Product, Design, software engineering teams, and clinical and operational subject matter experts to turn validated AI capabilities into reliable tools for clinicians, clinical coders, and revenue cycle teams. Work includes embedded features in existing products and standalone internal applications. Success is measured by delivering reliable, user-centered AI applications that measurably improve the effectiveness, efficiency, and quality of clinical, coding, and revenue cycle workflows across Accuity. Accuity partners with hospitals and health systems through a technology-enabled, physician-led model focused on clinical documentation integrity, coding accuracy, reimbursement optimization, and quality outcomes.

Requirements

Bachelor’s degree in computer science, software engineering, human-computer interaction, or a related technical field, or equivalent practical experience.
Three or more years of software engineering, application engineering, or product engineering experience, including responsibility for production applications or user-facing features.
Experience building applications or features using large language models or other AI services through APIs.
Experience designing and refining prompts for defined application use cases.
Experience integrating internal or third-party AI and machine learning services into existing applications.
Experience addressing service latency, cost, reliability, error handling, and graceful failure.
Working knowledge of model capabilities, limitations, prompting, retrieval, and AI-assisted application design.
Experience implementing explainability and observability for AI-powered applications, including traceable outputs, source citations, structured logging, and monitoring that help users and support teams understand system behavior.
Healthcare data experience; familiarity with clinical coding, CDI, claims, or revenue cycle data.

Nice To Haves

Relevant advanced education, professional training, or technical certifications.
Experience evaluating AI tools, APIs, or vendor products against technical and product requirements.
Experience contributing to build, buy, or integration decisions.
Experience partnering closely with product management and design on user-facing features.
Experience designing user interactions for AI-generated content, recommendations, or automated actions.

Responsibilities

Design, build, test, and maintain applications, features, and internal tools that use AI models, services, and agents provided by internal teams or approved vendors.
Translate user and business problems into AI application requirements, including expected and prohibited behavior, failure handling, and human review.
Build embedded product features or standalone applications according to workflow needs, and integrate AI services with interfaces, workflows, and data systems without duplicating existing platforms or infrastructure.
Prototype AI capabilities and define clear application-to-service interfaces, including request and response formats, error handling, latency requirements, and usage constraints.
Write clean, secure, maintainable, reviewable production code and participate in code reviews, technical design, testing, and releases.
Design and refine prompts, examples, structured outputs, and interaction patterns for specific use cases.
Present AI-generated content, evidence, citations, uncertainty, and limitations clearly, and provide appropriate review, editing, confirmation, and recovery options.
Partner with Product and Design on AI interaction patterns; determine when features should act automatically, request confirmation, or defer to a person; and build feedback mechanisms for user corrections and overrides.
Apply accessibility and usability standards to AI-powered interfaces.
Define measurable acceptance criteria and build repeatable tests for expected, unusual, and high-risk scenarios, including regression tests for prompts, service integrations, and model or configuration changes.
Evaluate generated content, retrieval results, citations, structured outputs, tool calls, and behavior when AI services are incorrect, incomplete, delayed, or unavailable.
Analyze failure patterns with AI Engineering and Data Science, document known limitations, ensure product behavior reflects them, and escalate requirements that available services cannot reliably support.
Own AI-powered application features from technical design through production release and ongoing maintenance; develop automated tests and follow source control, code review, continuous integration, and deployment practices.
Implement logging, telemetry, and monitoring; monitor reliability, latency, usage, and cost; investigate and resolve production issues; and maintain technical documentation on architecture, dependencies, configuration, support procedures, and limitations.
Work with platform and engineering teams to meet security, performance, availability, and support requirements.
Evaluate third-party AI products, APIs, and tools against product requirements, cost, reliability, security, and data-handling constraints; run structured trials; compare vendor claims with observed performance; and document limitations.
Recommend build, buy, or integration approaches with AI Engineering and Product, monitor relevant AI tools and services, and support selected vendor integrations and ongoing evaluation.
Build applications in accordance with HIPAA, HITRUST, PHI protection requirements, Accuity policy, approved technical environments, and applicable contractual requirements.
Preserve human review and decision traceability where clinical, coding, or financial judgment is involved; safeguard against data disclosure, unauthorized access, unsafe inputs, prompt injection, and unintended system actions.
Communicate AI feature behavior, supporting evidence, and limitations; escalate designs that could put PHI, patient safety, or clinical decision quality at risk; and prepare documentation and evidence for security, compliance, and audit review.
Partner with AI Engineering, Data Science, Product, Design, software engineering, clinicians, coders, and operational subject matter experts to understand requirements, capabilities, limitations, workflows, and application behavior.
Communicate tradeoffs involving performance, cost, accuracy, usability, and risk to technical, clinical, and business audiences; document decisions, requirements, risks, and unresolved questions; and contribute to shared engineering standards and reusable patterns.
Perform additional responsibilities as needed to support data science, technology, and organizational goals.