Clinical Data & AI Engineer

InnovoCommerce; Irvine (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

InnovoCommerce is a leading provider of Clinical AI solutions for the global life sciences industry. We’re seeking a Clinical Data & AI Engineer with a startup mindset to build AI on top of the clinical trial data flow, from protocol through study build, EDC, monitoring, and submission.

This role turns clinical standards and study structure into working AI behavior: deciding what should be deterministic, where models add value, and how to prove the output is right.

Qualifications

• Hands-on experience with clinical trial data in protocol, CRF/EDC, data management, or SDTM.
• Working knowledge of CDISC standards (CDASH, SDTM, controlled terminology, ODM).
• Has built production systems that use LLMs on structured data, including validating model output against a schema.
• Strong Python and SQL; comfortable with data modeling, versioning, and diffing structured data.
• Evaluation-first habit: deterministic outputs where possible, measured accuracy over impressions.
• Able to explain clinical data logic to engineers, and engineering constraints to clinical teams.

Responsibilities

• Build pipelines that turn protocols into structured study definitions (e.g. USDM, Biomedical Concepts) and carry them into downstream outputs like CRFs, EDC builds, and study documents.
• Ground AI output in CDISC standards, deciding what should be deterministic and where models add value
• Integrate with clinical systems such as EDC and CTMS, keeping every data flow auditable
• Build evaluation sets with deterministic expected outputs from primary standards and real study data
• Support risk-based monitoring with metrics computed from clinical data rather than inferred by models
• Commute to the office when necessary for in‑person collaboration (SoCal location necessary)

Skills

Python

SQL

CDISC standards

LLMs on structured data

Data modeling

Version control

Diffing data

Tools

Databricks

Delta Lake

Unity Catalog

Delta Sharing

Job description

InnovoCommerce is a leading provider of Clinical AI solutions for the global life sciences industry. We’re seeking a Clinical Data & AI Engineer with a startup mindset to build AI on top of the clinical trial data flow, from protocol through study build, EDC, monitoring, and submission. This role turns clinical standards and study structure into working AI behavior: deciding what should be deterministic, where models add value, and how to prove the output is right. You’ll work alongside our agent harness team, owning the clinical data and logic the agents run on.

Key Responsibilities:

• Build pipelines that turn protocols into structured study definitions (e.g. USDM, Biomedical Concepts) and carry them into downstream outputs like CRFs, EDC builds, and study documents
• Ground AI output in CDISC standards, deciding what should be deterministic and where models add value
• Integrate with clinical systems such as EDC and CTMS, keeping every data flow auditable
• Build evaluation sets with deterministic expected outputs from primary standards and real study data
• Support risk-based monitoring with metrics computed from clinical data rather than inferred by models
• Commute to the office when necessary for in‑person collaboration (SoCal location necessary)

Qualifications:

• Hands‑on experience with clinical trial data in at least one part of the flow: protocol, CRF/EDC build, data management, or SDTM
• Working knowledge of CDISC standards (e.g. CDASH, SDTM, controlled terminology, ODM)
• Has built production systems that use LLMs on structured data, including validating model output against a schema or reference
• Strong Python and SQL; comfortable with data modeling, versioning, and diffing structured data
• Evaluation‑first habit: deterministic expected outputs where possible, measured accuracy over impressions
• Able to explain clinical data logic to engineers, and engineering constraints to clinical teams

Preferred Qualifications:

• Risk‑based monitoring experience (e.g. RACT, KRIs, QTLs, ICH E6(R3))
• Regulated software background (e.g. GxP, 21 CFR Part 11)
• Has built agent systems beyond framework defaults, including tool design, context management, and evaluation of agent behavior
• Experience with Databricks (e.g. Delta Lake, Unity Catalog, Delta Sharing)