Saved to your account, encrypted. The AI that reads it doesn't keep it or train on it.
Full job description
From Hipp Health’s careers site
About Hipp
Hipp is an AI-native healthcare platform built to modernize operations for non-hospital healthcare providers. Our platform brings clinical workflows, billing infrastructure, scheduling, documentation, patient engagement, and operational data into a single intelligent system.
Healthcare organizations operate within detailed payer, regulatory, clinical, and documentation requirements. Hipp helps practices manage that complexity through software designed around real provider workflows, with AI and automation embedded throughout the platform.
Role Overview
Show full descriptionShow less
We’re looking for an AI Agent Engineer to build systems that help healthcare practices operate accurately, consistently, and in alignment with regulatory and payer requirements.
You will develop agents that can review documentation, identify missing or inconsistent information, apply configurable policies, explain findings, and guide users toward resolution. You will also build the evaluation, audit, and human-review infrastructure required for agents operating in high-stakes environments.
This role requires strong engineering judgment. Compliance agents must be helpful without overreaching, explain their reasoning without presenting unsupported conclusions, preserve auditability, and escalate appropriately when policy interpretation or human judgment is required.
What You’ll Do
Design and ship AI agents for documentation review, workflow compliance, policy checks, and operational quality assurance
Convert complex requirements into testable agent workflows, tools, policies, and decision boundaries
Build retrieval systems that ground agent behavior in approved policies, contracts, payer rules, and internal guidance
Develop structured review workflows that surface missing information, inconsistencies, exceptions, and recommended next actions
Create clear citations, evidence trails, and audit logs for agent outputs and actions
Design human-review and approval mechanisms for high-risk or ambiguous decisions
Build rigorous evaluations for factual grounding, policy adherence, consistency, recall, precision, and safe escalation
Partner with compliance, clinical, billing, product, and engineering stakeholders to define requirements
Monitor production agent behavior and investigate failures, regressions, or unexpected patterns
Build versioning and change-management mechanisms for policies, prompts, models, and evaluation datasets
Apply privacy-by-design and least-privilege principles to agent tools and data access
Contribute reusable agent infrastructure and engineering standards across Hipp
What We’re Looking For
Demonstrated experience building AI agents, agentic systems, or substantial LLM-powered products
Strong software engineering skills and the ability to build secure, maintainable production systems
Experience with tool-using agents, retrieval, structured outputs, workflow orchestration, or model evaluations
Experience grounding AI systems in authoritative source material
A strong understanding of agent reliability, traceability, observability, and failure handling
Ability to distinguish between probabilistic model behavior and decisions requiring deterministic enforcement
Experience building integrations with APIs, databases, document systems, or internal services
Proficiency in Python, TypeScript, or a comparable programming language
Strong analytical judgment and attention to detail
Clear written communication, particularly when explaining technical behavior and system limitations
Comfort collaborating with domain experts to translate nuanced rules into practical product behavior
We do not require a prescribed number of years of experience. We are looking for candidates who can demonstrate meaningful work building agents or AI systems that must be accurate, explainable, and reliable.
Nice to Have
Experience in healthcare, healthtech, insurance, fintech, legal technology, or another regulated domain
Familiarity with HIPAA, SOC 2, healthcare documentation, payer requirements, or audit processes
Experience building policy engines, rules systems, or case-management workflows
Experience with document intelligence, semantic retrieval, knowledge graphs, or provenance systems
Familiarity with model risk management and responsible-AI practices
Experience designing red-team tests or adversarial evaluations for agents
Experience implementing role-based access control, data retention, or audit logging
Startup or early-stage product experience
Why Join Hipp
Build AI systems for consequential workflows where quality and trust matter
Help define Hipp’s standards for safe, auditable, and reliable agents
Work directly with domain experts and customers
Shape foundational agent infrastructure across the product
Join a small team with significant technical and product ownership
Help healthcare providers manage complexity while remaining focused on patient care