AI-Powered Data Engineer for Enterprise Discovery

Bristol Myers Squibb; Princeton (KY); On-site; USD 88,000 - 106,000; Full time

Benefits offered by this job

Health coverage

Wellbeing programs

401(k) and insurance

Job summary

Bristol Myers Squibb is seeking an AI & Data Engineer to join the Data Discovery Services team in Princeton, NJ. You will build Python pipelines, enrich metadata, and contribute to semantic knowledge layers to enhance enterprise data discovery and AI retrieval.

You will work alongside data engineers, search engineers, and data scientists to deliver reliable data foundations, scalable pipelines, and API endpoints for applications and AI agents.

Qualifications

• Bachelor’s degree in computer science, data science, information science, engineering, or related field.
• Proven data/engineering background with production pipelines.
• Proficient Python as primary language.
• Proficient SQL skills.
• Experience with Databricks and AWS Glue for data pipelines.
• Strong fundamentals in ETL/ELT, data modeling and data quality.
• Familiarity with AWS services (S3, Glue) and OpenSearch/Elasticsearch.
• Good communication and collaboration skills.

Responsibilities

• Build and maintain Python pipelines that pull metadata from data catalogs, enrich it with taxonomy tags, and publish to the discovery platform.
• Tune and optimize search indexes and queries to match user needs.
• Develop a semantic knowledge layer with vector embeddings to support RAG and AI systems.
• Maintain integrations to sync ontology changes into the discovery platform.
• Investigate and resolve data pipeline issues across Databricks and AWS Glue; implement data quality checks.
• Build API endpoints and MCP servers to expose search and metadata capabilities.
• Design metadata pipelines mapping cross-domain dataset relationships with confidence scores.
• Analyze search patterns and user feedback to improve discovery over time.

Skills

Python

SQL

Databricks

AWS Glue

OpenSearch/Elasticsearch

Metadata management

Communication skills

Problem-solving

Education

Bachelor’s degree in Computer Science or related field

Master’s degree preferred

Tools

Databricks

AWS Glue

OpenSearch/Elasticsearch

Job description

Bristol Myers Squibb is seeking an AI & Data Engineer to join the Data Discovery Services team in Princeton, NJ. You will build Python pipelines, enrich metadata, and contribute to semantic knowledge layers to enhance enterprise data discovery and AI retrieval.

You will work alongside data engineers, search engineers, and data scientists to deliver reliable data foundations, scalable pipelines, and API endpoints for applications and AI agents.