Agentic AI Data Engineer for CMC Data Backbone

BioSpace; Indianapolis (IN); On-site; USD 65,000 - 169,000; Full time

Benefits offered by this job

401(k) plan

Pension

Vacation

Job summary

Lilly in Indianapolis seeks an AI Data Engineer to build the data ingestion infrastructure and a unified data model for the CMC Data Backbone. This hands-on role writes production‑quality pipelines, defines CMC data schemas, and collaborates with scientists and digital architects to ensure data from LIMS/ELN and external CDMO partners flows into a single backbone.

You will own components end‑to‑end, work on agentic pipelines, HITL workflows, validation, and data quality while ensuring 21 CFR

Qualifications

• MS or BS with 1–2 (MS) / 3–5 years (BS) data engineering experience.
• Proficiency in Python and SQL; production‑quality code ownership.
• Experience building ETL/ELT pipelines from unstructured sources.
• Hands‑on experience with LLM‑powered apps: retrieval‑augmented generation, tool‑calling, orchestration.
• Cloud data platforms: Azure or AWS.
• Relational data modeling and schema design expertise.
• Familiarity with data orchestration tools (Airflow or similar).
• Authorized to work in the United States on a full‑time basis.

Responsibilities

• Design and implement agentic pipeline components within the orchestration framework.
• Develop HITL workflows, review queues, and audit trails for FDA compliance.
• Build AI‑assisted ingestion pipelines from PDFs, Excel, and vendor exports.
• Implement validation, reconciliation, and exception handling for data integrity.
• Create monitoring, alerting, and reusable pipeline templates.

Skills

Python

SQL

ETL/ELT

LLM apps

Azure

AWS

Airflow

Data modeling

Education

MS in Computer Science

BS in Computer Science

Tools

LangGraph

LlamaIndex

GitHub Actions

Azure Data Factory

Databricks

Job description

Lilly in Indianapolis seeks an AI Data Engineer to build the data ingestion infrastructure and a unified data model for the CMC Data Backbone. This hands-on role writes production‑quality pipelines, defines CMC data schemas, and collaborates with scientists and digital architects to ensure data from LIMS/ELN and external CDMO partners flows into a single backbone.

You will own components end‑to‑end, work on agentic pipelines, HITL workflows, validation, and data quality while ensuring 21 CFR