AI Agent Engineer – Compliance

This is a fully remote position, open to applicants in United States.

📋 Description

• Design and implement AI agents for the review of documentation, ensuring workflow compliance, conducting policy checks, and maintaining operational quality assurance.

• Transform intricate requirements into testable workflows for agents, tools, policies, and decision parameters.

• Create retrieval systems based on approved policies, contracts, payer regulations, and internal guidelines.

• Develop structured review processes that highlight missing information, inconsistencies, exceptions, and suggest next steps.

• Generate citations, evidence trails, and audit logs for the outputs and actions of agents.

• Establish human review and approval protocols for high-risk or ambiguous decisions.

• Create evaluations focused on factual grounding, adherence to policy, consistency, recall, precision, and safe escalation.

• Collaborate with compliance, clinical, billing, product, and engineering teams to outline the requirements.

• Oversee the behavior of production agents and investigate failures, regressions, or unexpected patterns.

• Develop version control and change management systems for policies, prompts, models, and evaluation datasets.

• Implement privacy-by-design and least-privilege principles in agent tools and data access.

• Contribute to reusable agent infrastructure and engineering standards across Hipp.

⛳️ Requirements

• Proven experience in building AI agents, agentic systems, or significant LLM-powered products.

• Strong software engineering capabilities with a focus on creating secure and maintainable production systems.

• Experience with tool-using agents, retrieval mechanisms, structured outputs, workflow orchestration, or model evaluations.

• Familiarity with grounding AI systems in authoritative source materials.

• A solid understanding of agent reliability, traceability, observability, and failure management.

• Ability to differentiate between probabilistic model behaviors and decisions that necessitate deterministic enforcement.

• Experience in integrating with APIs, databases, document management systems, or internal services.

• Proficiency in Python, TypeScript, or a similar programming language.

• Strong analytical skills and attention to detail.

• Excellent written communication skills, especially in explaining technical behaviors and system limitations.

• Comfort in collaborating with domain experts to translate intricate rules into functional product behaviors.

• Experience in healthcare, healthtech, insurance, fintech, legal technology, or other regulated sectors.

• Knowledge of HIPAA, SOC 2, healthcare documentation, payer requirements, or auditing processes.

• Experience in developing policy engines, rules systems, or case management workflows.

• Familiarity with document intelligence, semantic retrieval, knowledge graphs, or provenance systems.

• Understanding of model risk management and responsible AI practices.

• Experience in designing red team tests or adversarial evaluations for agents.

• Experience with implementing role-based access control, data retention policies, or audit logging.

• Background in startup or early-stage product development.

• Must clarify whether employer-sponsored work authorization will be necessary to work in the United States.

🏝️ Benefits

• Develop AI systems for critical workflows where quality and trust are paramount.

• Assist in establishing Hipp’s standards for safe, auditable, and reliable agents.

• Engage directly with domain experts and customers.

• Influence the foundational agent infrastructure across the product.

• Join a small team with substantial technical and product ownership.

• Aid healthcare providers in managing complexity while keeping the focus on patient care.