Principal Applied AI & Knowledge Engineer

At Claritev, our mission is to simplify healthcare workflows, improve transparency, and bend the healthcare cost curve. We believe that data, technology, and AI can fundamentally transform how healthcare operates by automating complex workflows, improving decision-making, and reducing unnecessary costs across the system.

By combining deep healthcare expertise with advanced analytics and AI, we help payers, providers, and employers operate more efficiently and deliver better outcomes for the people they serve.

We are bold in our thinking, rigorous in execution, and committed to service excellence for every stakeholder. Our culture values innovation, accountability, diversity of thought, and collaboration.

Join us as we accelerate our transformation into a leading technology and AI-driven company shaping the future of healthcare.

JOB SUMMARY

• We are seeking Principal Applied AI Engineer to help build and evolve Claritev’s AI platform and implement high-impact AI opportunities. One initial focus of this role is to help build and evolve the enterprise Context & Knowledge Layer within the AI platform, which enables AI agents and applications to efficiently and accurately contextualize our data, products, business processes, enterprise systems, industry concepts, and institutional knowledge. Additionally, the role will have opportunities to contribute to other parts of Claritev's AI platform, products, and workflows.
• This is a hands-on Principal-level engineering role that also involves working directly with technical and business stakeholders to understand requirements, make architecture decisions, and turn ambiguous needs into scalable production systems. You will design and build production capabilities while helping establish the patterns, tooling, and engineering practices used to create, operate, maintain, govern, evaluate, and continuously adapt enterprise agentic AI, knowledge, and context.
• The ideal candidate combines broad proficiency in modern AI with a background in context and knowledge systems. You should be highly proficient in generative and agentic AI while also bringing practical experience with knowledge graphs, ontologies, semantic technologies, and retrieval. A strong understanding of software and data architecture and production engineering will also be necessary.

JOB ROLES AND RESPONSIBILITIES

• Lead the architecture, development, deployment, and operation of production AI applications, services, and platforms.
• Design and implement knowledge graphs, ontologies, semantic models, RAG retrieval systems, context graphs, human-in-the-loop controls, and mechanisms that connect them to AI agents.
• Establish reusable frameworks, APIs, MCPs, code components, and engineering patterns that enable teams to build and deploy AI solutions efficiently and consistently.
• Drive end-to-end delivery from prototype through production, including integration with enterprise systems, monitoring, observability, evaluation, and ongoing improvement.
• Build agentic workflows that manage ingestion, extraction, normalization, linking, validation, curation, governance, and continuous update of enterprise knowledge from heterogeneous sources including structured and unstructured data.
• Work directly with business and operations stakeholders to discover domain concepts, intents, workflows, constraints, and tacit knowledge and translate them into technical representations and platform capabilities.
• Partner with AI engineers, software engineers, data engineers, infrastructure teams, security, governance, and subject matter experts to integrate knowledge and agentic solutions into production.
• Establish quality standards for both AI agents and knowledge, including offline and online evaluations, reliability, latency, cost, safety, and performance.
• Ensure secure and responsible use of AI, including privacy, PHI/PII protection, explainability, auditability, and compliance with HIPAA and applicable data-governance requirements.
• Provide technical leadership across complex, cross-functional initiatives; influence architecture and engineering decisions beyond an individual project.
• Mentor engineers and data scientists to promote a culture of technical excellence, continuous learning, and pragmatic innovation.

REQUIREMENTS (Education, Experience, and Training)

Education

• Bachelor’s degree in Computer Science, Engineering, Data Science, or a related quantitative field required.
• Master’s degree or PhD preferred.

Experience

• 10+ years of hands-on experience in software engineering, machine learning engineering, applied AI, or a related technical discipline.
• 5+ years of experience designing and delivering production-grade ML or AI systems.
• 3+ years of experience building with generative AI, LLMs, RAG, and/or agentic AI systems.
• Demonstrated experience leading complex technical initiatives from concept through production deployment and measurable business impact.

General Technical Skills

• Strong software engineering skills, including expert-level Python proficiency and experience designing scalable services, APIs, and distributed systems.
• Foundation in machine learning, statistics, and optimization.
• Experience with agentic AI frameworks and patterns, such as LangGraph, LangChain, etc.
• Experience designing AI agents with tool use, planning, orchestration, memory, and guardrails.
• Experience developing evaluation and observability capabilities for LLM and ML systems, including accuracy, reliability, safety, latency, and cost.
• Understanding of MLOps/LLMOps and lifecycle management practices including CI/CD, model and prompt versioning, monitoring, experimentation, and incident troubleshooting.

Context and Knowledge Skills

• Hands-on experience with knowledge graphs and graph data modeling, including a good understanding of both labeled property graph (LPG) and RDF-based approaches, and familiarity with databases such as Neo4j, AWS Neptune, or similar.
• Strong understanding of ontologies, semantic modeling, entity and relationship modeling, schema evolution, and knowledge representation concepts.
• Experience with vector databases, embeddings, RAG, and approaches like GraphRAG.
• Experience with graph query languages and tooling such as Cypher, SPARQL, RDFS, OWL, SHACL, Protégé, and comparable technologies.
• Experience designing or implementing systems for knowledge extraction, entity resolution, relationship extraction, provenance, metadata enrichment, or automated knowledge curation from heterogeneous enterprise sources.
• Understanding of graph algorithms such as community detection and pathfinding.

Other Skills

• Strong problem-solving, critical-thinking, communication, and organizational skills.
• Ability to communicate complex technical concepts clearly to technical and non-technical stakeholders.
• Ability to operate effectively in a fast-moving, cross-functional environment.

Preferred Qualifications

• Experience in healthcare, health technology, insurance, claims, or other regulated industries.
• Experience building AI systems that process sensitive data, including PHI or PII.
• Experience with analytical data architectures and enterprise metadata/catalog systems.
• Experience with deep-learning frameworks such as PyTorch or TensorFlow.

COMPENSATION

The salary range for this position is $190k - 210k. Specific offers take into account a candidate’s education, experience and skills, as well as the candidate’s work location and internal equity. This position is also eligible for health insurance, 401k and bonus opportunity.

#LI-MZ1