Agentic AI in Center of Excellence

RAAPID, Inc.; Louisville (KY); On-site; USD 120,000 - 180,000; Full time

Job summary

RAAPID, a Louisville-based healthcare technology company, is establishing an Agentic AI Center of Excellence to design, deploy, and scale autonomous AI agents across its risk-adjustment platform.

The role is hands-on IC, focusing on building AI agents, deploying to production, and maintaining their health while improving accuracy and cost efficiency. Collaboration with Sales, Product, and Operations is essential to translate workflows into production-ready systems.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, Information Technology, or related field.
• Portfolio with 3–5 repos showing hands-on work with LLMs or AI APIs.
• 2+ years of software engineering; 1+ year building, deploying and maintaining AI-enabled applications.

Responsibilities

• Build, deploy, maintain, and improve autonomous AI agents.
• Integrate AI agents with CRM, EHR/FHIR endpoints, databases and enterprise tools.
• Collaborate with CoE Translators and Champions to turn workflows into production-ready agent architectures.
• Ensure guardrails for PHI/PII and HIPAA/HITRUST compliance; optimize cost and latency.

Skills

Python

SQL

Node.js/TypeScript

Education

Bachelor’s or Master’s degree in Computer Science/Software Engineering/Information Technology

Tools

LangChain

LlamaIndex

AutoGen

CrewAI

LangGraph

Semantic Kernel

Git

Docker

FastAPI

FastStream

LangSmith

Ragas

Azure

AWS

GCP

PostgreSQL

MongoDB

Pinecone

Qdrant

Neo4j

Job description

RAAPID is a leading healthcare technology innovator specializing in AI-enabled risk adjustment solutions. Funded by Microsoft and Great Place to Work-certified organization, we serve payers, healthcare providers, and support organizations with cutting-edge technology solutions that optimize revenue, ensure compliance, and reduce administrative costs.

Why RAAPID?

• Backed by an unprecedented Industry Trifecta: M12 (Microsoft's Venture Fund), UPMC Enterprises, and Healthworx (CareFirst) - RAAPID is the only risk adjustment platform validated by a global technology giant, a world-class health system, and a top-tier payer investor simultaneously.
• Industry Pioneer: Leveraging state-of-the-art artificial intelligence, machine learning, vision AI, and knowledge graphs to transform healthcare operations.
• Strong Foundation: Built on four key pillars - Trust, Technical Competence, Stability, and Technical Innovation
• Recognition: Proud recipient of HITRUST certification, demonstrating our commitment to security and compliance
• Culture: Certified Great Place to Work, reflecting our dedication to employee satisfaction and professional growth
• Mission-Driven: Focused on revolutionizing value-based healthcare through customizable, AI-powered solutions
• Global Presence: Headquartered in Louisville, Kentucky, with a robust team of over 100 employees across the US and India

Position Overview - Applied AI Engineer

We are establishing an Agentic AI Center of Excellence (CoE) to design, build, and deploy the next generation of autonomous digital workers across RAAPID. We are seeking pragmatic, high-velocity Applied AI Engineers, Senior Applied AI Engineers, and Principal Applied AI Engineers to join this specialized team as core “Builders.” This is a pure Individual Contributor (IC) track designed for engineers who love being hands-on with code and shipping production AI systems.As a Builder, you will not just write code in a sandbox - you will own the entire lifecycle of your creations. You will be responsible for building AI agents, deploying them to production, maintaining their operational health, and continuously improving their accuracy, cost-efficiency, and user experience based on real-world usage and structured evaluation. You will work closely with CoE Champions (functional sponsors across Sales, Marketing, Product, Operations, HR, Legal, and Finance) and Translators (understanding of product + building) to convert business workflows into production-grade agentic systems that move the needle on revenue, efficiency, and quality of care.

• End-to-End Lifecycle Ownership (Build, Deploy, Maintain & Improve)

1. Build: Design and code autonomous AI agents, custom API tools, and Retrieval-Augmented Generation (RAG) pipelines using modern orchestration frameworks (LangGraph, CrewAI, AutoGen, etc).
2. Deploy: Set up robust deployment pipelines to move AI agents from local MVPs to production-grade environments using Docker, APIs, microservices, and cloud infrastructure.
3. Maintain: Take full responsibility for the operational health of your deployed agents - monitor uptime, handle error states, manage token/cost limits, and ensure day-to-day reliability.
4. Improve: Establish systematic evaluation loops (Evals) to measure agent accuracy. Continuously refine prompt structures, system guidelines, guardrails, and memory retrieval mechanisms to improve agent performance over time.

• Technical Implementation & Data Foundation

1. Agentic Frameworks: Build and manage autonomous AI agents for tasks such as lead prospecting, market segmentation, content generation, claims/coding workflows, operations management, and data synthesis.
2. Data Integration: Implement and optimize indexing, hybrid search, and RAG pipelines using vector databases (Pinecone, Qdrant, Milvus, Chroma) or knowledge graphs (Neo4j) to supply high-context data to agents - critical for RAAPID’s grounded use cases.
3. API Integration & Tooling: Connect LLMs to internal enterprise systems (CRM, EHR/FHIR endpoints, databases, operational tools) and external APIs, enabling agents to execute real-world actions safely.

1. AI Reasoning, Evaluations & Guardrails

1. Reasoning & Evaluation: Define, test, and run automated evaluation frameworks (Ragas, LangSmith, or custom eval datasets) to track latency, accuracy, safety, and hallucination rates across agent workflows.
2. Guardrails & Security: Implement strict guardrails to ensure agents operate safely, protect PHI/PII, and adhere to HIPAA, HITRUST, and other compliance standards intrinsic to healthcare AI.
3. Cost & Latency Optimization: Tune model selection, caching, batching, and prompt design to keep token economics and end-to-end latency within production SLOs.

• Cross-Functional Collaboration

1. Collaborate with Translators: Partner with CoE Translators to convert business workflows into production-ready agent architectures, treating their domain context as a first-class design input.
2. Support Business Units: Act as a technical advisor to Sales, Marketing, Product, Operations, HR, Legal, and Finance Champions on feasibility, ROI, and best practices for automating their workflows through Agentic AI.
3. Knowledge Sharing: Document architectural decisions, share reusable agent patterns, and contribute to the CoE’s internal library of components, prompts, evals, and guardrails.

• Technical Degree: Bachelor’s or Master’s degree in Computer Science, Software Engineering, Information Technology, or a related technical field.
• Provable Portfolio: A strong, active GitHub profile featuring at least 3 to 5 repositories demonstrating hands-on experience building, deploying, and maintaining software applications - ideally including at least one project that integrates LLMs or AI APIs and solves a real business problem.
• Experience Requirements by Level (Individual Contributor track):
  • Applied AI Engineer (IC): 2+ years of professional software engineering experience, with at least 1 year of hands-on experience building, deploying, and maintaining applications that integrate LLMs or AI APIs.
  • Senior Applied AI Engineer (IC): 5+ years of professional software engineering experience, with at least 2 years of hands-on experience putting complex AI systems (advanced RAG, multi-agent workflows, cognitive reasoning architectures) into production, with clear ownership of post-deployment maintenance and improvement.
  • Principal Applied AI Engineer (IC): 8+ years of professional software engineering experience, with at least 3 years putting production-grade agentic systems into the hands of real users. Demonstrated ownership of cross-cutting architecture, evaluation strategy, and platform-level decisions that other engineers depend on. Acts as the senior-most technical voice for the CoE without people-management responsibilities.
• Problem-Solving Mindset: Demonstrable passion for identifying business bottlenecks and building software to automate or solve them - evidence of having shipped something that someone actually used.

Preferred Qualifications

• Agentic Frameworks: Hands-on experience with multi-agent orchestration libraries (CrewAI, AutoGen, LangGraph, etc).
• Data & RAG Systems: Experience with Vector Databases (Pinecone, Qdrant, Milvus, Chroma) and advanced retrieval techniques (hybrid search, reranking, query rewriting, GraphRAG).
• LLM Evaluation & Ops: Experience building LLM evaluation suites (Evals) and monitoring agents in production using LangSmith, Ragas, or comparable tooling.
• Cloud & Deployment: Familiarity with deploying applications to cloud environments (Azure preferred; AWS or GCP acceptable) using containerization (Docker, Kubernetes).
• Healthcare/Regulated Domain Exposure: Prior work in healthcare, fintech, or other regulated industries - especially familiarity with FHIR, HL7, HEDIS, HCC/risk adjustment concepts, or HIPAA-compliant architectures - is a strong plus.
• Specialization Tracks: We are particularly interested in candidates who bring depth in one of three areas - (a) AI Reasoning / LLM expertise & Evals, (b) Data Foundation (indexing, retrieval, knowledge graphs), or (c) end-to-end Agent Engineering and tool integration.

Technical Skills

• Languages: Python (highly preferred), SQL, Node.js / TypeScript.
• AI Frameworks: LangChain, LlamaIndex, AutoGen, CrewAI, LangGraph, Semantic Kernel.
• Databases: PostgreSQL, MongoDB, Pinecone, Qdrant, Neo4j.
• Tools: Git, Docker, FastAPI / FastStream, LangSmith, Ragas (for tracing and evals).
• Cloud: Azure (preferred), AWS, or GCP - with containerization and CI/CD experience.

Core Competencies

• The “Builder” Instinct - a bias for action; prefers writing clean code and shipping working software over endless theoretical discussions.
• Pragmatic Creativity - finds creative ways to make LLMs behave reliably despite non-deterministic outputs.
• Technical Aptitude & Adaptability - fast learner who can adjust as the AI tooling landscape changes.
• Ownership & Operational Discipline - owns what they ship, end to end, including the unglamorous maintenance work.
• Collaborative Communication - articulates technical constraints and possibilities clearly to non-technical CoE members.
• Evidence-Driven Iteration - instinctively reaches for evals, metrics, and traces before reaching for opinions.

• Competitive compensation package commensurate with level and experience.
• Opportunity to be a founding member of a high-impact Agentic AI Center of Excellence - with direct visibility to product, GTM, and executive leadership.
• Access to modern computational resources, frontier model APIs, and direct partnership benefits from our Microsoft / M12 ecosystem.
• A clear Individual Contributor growth path (Applied → Senior → Principal Applied AI Engineer) that rewards deep technical mastery without forcing engineers into people management.
• A collaborative, fast-paced, and highly innovative work environment with low ceremony and high autonomy.