Postdoc: AI Evaluation & Standards for Clinical Ops

Jobtailor; Antwerpen; Sur place; EUR 70 000 - 110 000; Plein temps

Résumé du poste

Jobtailor seeks a researcher to design evaluation frameworks and rubrics for AI agents operating in clinical operations and global development settings. You will define quality dimensions for outputs such as clinical data queries, anomaly detection, and regulatory Q&A content, working with SME s and engineers.

The role involves building benchmark datasets, running human evaluation protocols, and translating findings into measurable improvements for regulated pharma environments.

Qualifications

• PhD or equivalent research experience in a clinical, biomedical, regulatory, biostatistics, or closely related field.
• Strong interest in hands-on work with generative AI and agentic systems.
• Curiosity about LLM behavior in specialized domains and failure modes.
• Proven ability to develop evaluation frameworks, rubrics, and structured assessment protocols.

Responsabilités

• Develop evaluation frameworks and rubrics for AI agents in clinical operations and global development contexts.
• Define quality dimensions for outputs like clinical data queries, anomaly detection, and regulatory documents.
• Design and run human evaluation protocols with clinical, regulatory, and site-facing experts.
• Build benchmark datasets and evaluation pipelines used across AI applications.

Connaissances

Python

ML/Data stack

Analytical writing

Interdisciplinary collaboration

Quality assessment design

Formation

PhD in Clinical/ Biomedical/ Regulatory/ Biostatistics

Outils

LLM APIs

Vector databases

Description du poste

Jobtailor seeks a researcher to design evaluation frameworks and rubrics for AI agents operating in clinical operations and global development settings. You will define quality dimensions for outputs such as clinical data queries, anomaly detection, and regulatory Q&A content, working with SME s and engineers.

The role involves building benchmark datasets, running human evaluation protocols, and translating findings into measurable improvements for regulated pharma environments.