Senior AI Engineer - Data Scientist

Tria Federal

About The Position

We’re seeking a Senior AI Engineer / Data Scientist to lead the design, deployment, and scaling of enterprise AI capabilities—specifically large language model (LLM) solutions, LLMOps practices, and the development of a healthcare ontology/knowledge graph to enhance a complex data environment.

Requirements

Education/Experience: 10+ years with BS/BA; 8+ years with MS/MA; 5+ years with PhD in Computer Science, Data Science, or related field.
Hands-on experience with LLMs and GenAI solutions, including prompt engineering, RAG architecture, and LLMOps practices.
Proven experience in ontology design and knowledge graph development for complex data-driven systems.
Experience with Databricks, Snowflake, and AWS Cloud Services.
Proficiency in Python and SQL (Snowflake SQL).
Experience with CI/CD workflows and automated deployments.
Familiarity with Scaled Agile Framework (SAFe).
Excellent communication skills and ability to work independently.
US Citizenship required.

Nice To Haves

Experience with Databricks E2 components (Unity Catalog, Feature Store).
Knowledge of CMS systems and Medicare/Medicaid data.
Familiarity with LLM/GenAI tooling (LangChain, LlamaIndex, Hugging Face, AWS Bedrock).
Experience with vector databases and RAG orchestration.
Knowledge graph tools: Neo4j, TigerGraph, AWS Neptune, RDF/OWL, SPARQL, Gremlin, Cypher, Protégé.
Model lifecycle & governance: MLflow, Model Registry, feature stores, LLM safety testing.
Observability & automation: GitHub Actions/Jenkins, Terraform, Docker/Kubernetes, Prometheus/Grafana.

Responsibilities

Ontology & Knowledge Graph
Design and maintain a healthcare ontology to normalize CMS data across claims, providers, and workflows.
Build and manage knowledge graphs (RDF/OWL or property graph) to support semantic search, inference, and RAG augmentation.
Develop graph data pipelines for ingestion, transformation, and entity resolution aligned with governance standards.
Collaborate with SMEs to define controlled vocabularies and create reusable semantic APIs for analytics and AI.
GenAI & LLMOps
Architect and operationalize LLMs for production use cases including RAG, agentic workflows, and MCP tools.
Build LLM evaluation and safety frameworks (prompt quality, grounding, hallucination detection, bias checks) with automated testing and human-in-the-loop reviews.
Design cost- and latency-aware pipelines with observability for performance and reliability.
Implement LLMOps best practices: prompt versioning, CI/CD for artifacts, rollout strategies, and A/B testing.
Integrate vector databases and optimize chunking, embeddings, and retrieval for high-quality responses.
Platform & System Architecture
Support productionalization of AI/ML workflows with automated quality checks and lifecycle orchestration.
Ensure data security, governance, and CMS compliance.
Contribute to high-level system design for integrating new AI capabilities into a cloud-based analytics platform.
Maintain documentation and acceptance criteria for system changes.