AI Engineer

Accuity
•Remote

About The Position

The AI Engineer develops and operates AI systems that support automation across Accuity’s clinical documentation and revenue cycle workflows. Reporting to the Vice President, Data Science and AI, the role builds production services using large language models, intelligent agents, retrieval systems, knowledge graphs, and traditional machine learning. The engineer owns the technical systems that enable applications to use AI reliably and securely, including model integration and adaptation, agent orchestration, retrieval-augmented generation, vector and graph-based knowledge systems, Model Context Protocol services, evaluation pipelines, deployment automation, observability, and production support. The role works with proprietary and open-source models and selects an appropriate approach for each use case, such as prompt and context engineering, retrieval, fine-tuning, tool integration, classical machine learning, or a combination of techniques. It partners with Data Science to productionize validated approaches; with Platform Management and Data Architecture on infrastructure, data access, and governance; and with application engineering teams to deliver stable, reusable AI services. Success is measured by the reliability, security, maintainability, and measurable workflow impact of AI systems delivered across the Accuity ecosystem. The position is remote and exempt. It is an individual-contributor role with less than 10% travel. Physical demands are representative of an office role and include interacting with people and technology while sitting or standing, communicating by phone and email, and sitting for extended periods, with or without reasonable accommodations. Physical effort and exposure to physical risk are limited to those of an office environment.

Requirements

  • A master’s degree in computer science, artificial intelligence, machine learning, or a related technical field, or equivalent practical experience, is required.
  • At least 5 years of experience in software, AI/ML, or platform engineering, including ownership of production systems.
  • Hands-on experience developing and operating LLM applications, AI agents, and retrieval-augmented generation solutions.
  • Strong Python proficiency, including experience with AI/ML libraries, vector search, tool integration, and human-in-the-loop workflows.
  • Experience deploying and maintaining AI/ML systems using automated testing, evaluation, CI/CD, monitoring, and production controls.
  • Experience implementing AI observability, explainability, security, and governance practices.

Nice To Haves

  • A PhD in computer science, artificial intelligence, machine learning, or a related field.
  • Experience with Azure AI Foundry, Azure ML, Databricks, vector databases, or comparable AI platforms.
  • Familiarity with knowledge graphs, agent orchestration, Model Context Protocol (MCP), or model fine-tuning.
  • Healthcare data experience, particularly clinical coding, CDI, claims, or revenue cycle.
  • Experience taking ownership of externally developed systems.

Responsibilities

  • Build and maintain production systems using large language models, machine learning models, and intelligent agents.
  • Develop agent workflows using tools, retrieval, structured outputs, state, and human approval controls.
  • Select and adapt models through prompting, retrieval, fine-tuning, or other appropriate techniques.
  • Integrate AI systems with internal applications, data sources, APIs, and approved external services.
  • Build reusable AI services with clear, stable interfaces for application teams.
  • Develop retrieval-augmented generation systems using approved enterprise content and data.
  • Build and maintain document ingestion, embedding, indexing, search, reranking, and citation pipelines.
  • Implement vector databases, hybrid search, knowledge graphs, and graph-based retrieval where appropriate.
  • Maintain data provenance and access controls, and keep indexed information current.
  • Measure retrieval quality and correct missing, outdated, duplicated, or irrelevant results.
  • Build and maintain Model Context Protocol servers, clients, tools, and resources.
  • Define secure tool interfaces with clear schemas, permissions, validation, and failure handling.
  • Connect agents to approved applications, databases, APIs, and business systems.
  • Apply authentication, authorization, audit logging, and least-privilege access to agent tools.
  • Develop reusable integrations that support multiple AI applications.
  • Deploy and operate LLMs, agents, retrieval services, and machine learning models in production.
  • Maintain automated pipelines for testing, versioning, deployment, promotion, retraining, and rollback.
  • Track versions and lineage across models, prompts, tools, datasets, indexes, and configurations.
  • Monitor quality, reliability, latency, usage, and cost.
  • Investigate production failures and implement lasting corrective actions.
  • Build automated evaluation and regression testing for models, prompts, agents, retrieval systems, and tools.
  • Work with Data Science to turn evaluation methods and production thresholds into release controls.
  • Test systems against representative, unusual, adversarial, and high-risk scenarios.
  • Implement safeguards against prompt injection, data leakage, unauthorized tool use, and unsafe outputs.
  • Ensure AI systems comply with HIPAA, HITRUST, PHI protection requirements, and Accuity policy.
  • Preserve human review, decision traceability, and audit logging where clinical or coding judgment is involved.
  • Partner with Data Science to move validated AI approaches into production.
  • Partner with Platform Management and Data Architecture on infrastructure, deployment, data access, and governance.
  • Partner with application teams to deliver AI capabilities through reliable and documented services.
  • Assume ownership of systems delivered by internal teams or external development partners.
  • Write clean, secure, version-controlled code and maintain documentation that another engineer can use to operate the system.
  • Communicate system behavior, limitations, risks, and tradeoffs clearly to technical, clinical, and business audiences.
  • Perform additional responsibilities as needed to support data science, technology, and organizational goals.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service