Responsibilities
- Architect and deploy knowledge representation systems optimized for efficiency and cost, leveraging diverse storage types such as graph, document, tabular, and vector databases.
- Create, deploy, and manage entity resolution pipelines to accurately link and disambiguate records.
- Lead the development of embedding-based and hybrid models for semantic similarity, owning end-to-end implementation and improvements.
- Develop and maintain LLM-enhanced pipelines that extract ontological entities from unstructured and semi-structured healthcare and human services data.
- Design and integrate uncertainty quantification methods into knowledge representation outputs, including confidence scoring, score calibration, and data quality signal propagation.
- Work closely with data quality specialists to create feedback loops identifying root causes of pipeline errors and improving data integrity.
- Engage with internal teams and external partners to align on technical direction and deliver shared objectives.
- Maintain expertise in advancements across AI, machine learning, and data science, particularly in knowledge graph embeddings, neuro-symbolic systems, and reasoning frameworks.
Responsibilities
- Architect and deploy knowledge representation systems optimized for efficiency and cost, leveraging diverse storage types such as graph, document, tabular, and vector databases.
- Create, deploy, and manage entity resolution pipelines to accurately link and disambiguate records.
- Lead the development of embedding-based and hybrid models for semantic similarity, owning end-to-end implementation and improvements.
- Develop and maintain LLM-enhanced pipelines that extract ontological entities from unstructured and semi-structured healthcare and human services data.
- Design and integrate uncertainty quantification methods into knowledge representation outputs, including confidence scoring, score calibration, and data quality signal propagation.
- Work closely with data quality specialists to create feedback loops identifying root causes of pipeline errors and improving data integrity.
- Engage with internal teams and external partners to align on technical direction and deliver shared objectives.
- Maintain expertise in advancements across AI, machine learning, and data science, particularly in knowledge graph embeddings, neuro-symbolic systems, and reasoning frameworks.
