Clinical AI Intern
Wk
·Today
- Location
- CHE - Zurich, Switzerland
- Workplace
- Hybrid
- Type
- Internship
- Department
- Healthcare
- Seniority
- Internship
- Source
- Workday
Description
Role Overview
The intern will work on two objectives for Health Research AI and product management leadership.
- Gold-standard dataset development. Build clinician-annotated reference datasets for evaluating Ovid.com agentic outputs, including data extraction, quality appraisal, and certainty assessment. This work draws on clinical trial methodology, biostatistics, and evidence-based medicine.
- Workflow mapping and consolidation planning. Map the Ovid Guidelines AI (OGAI) workflow and the Ovid.com agentic workflow, identify synergies and redundancies, and plan the replacement or supplementation of OGAI workflow components with the more mature Ovid.com agentic workflow to reduce technical debt. This work draws on systems engineering.
The gold-standard datasets also serve as the validation reference for the consolidation plan.
Key Responsibilities
1. Gold-standard dataset development (clinical trials, biostatistics, evidence-based medicine)
- Define the scope of each reference set: clinical questions, guideline topics, and study designs (randomized trials, observational studies, systematic reviews and meta-analyses).
- Write annotation guidelines for PICO elements, study design, outcomes, and effect estimates (e.g., hazard ratios, risk ratios, confidence intervals, and derived measures such as ARR and NNT), with each value linked to its source paragraph or table.
- Produce reference ratings for risk of bias, quality appraisal, and certainty of evidence (Cochrane RoB 2, ROBINS-I, Newcastle-Ottawa Scale, AMSTAR 2, GRADE).
- Establish dual annotation and adjudication procedures with clinician reviewers, and report inter-annotator agreement.
- Version and document each dataset for benchmarking and regression testing of OGAI and Ovid.com outputs.
2. Workflow mapping and consolidation planning (systems engineering)
- Map the OGAI workflow end to end: inputs, agents and prompts, intermediate states, outputs, dependencies, and failure points across ingestion, data extraction, pooling, quality appraisal, GRADE certainty assessment, and guideline synthesis.
- Map the Ovid.com agentic workflow to the same level of detail, including retrieval, article classification, data extraction, quality appraisal, and verification.
- Produce a component-level crosswalk of the two workflows that identifies shared functions, synergies, redundancies, and gaps.
- Assess each OGAI component for replacement by, or supplementation with, the corresponding Ovid.com agentic component, with technical and clinical rationale.
- Define the target-state architecture, including shared schemas, data contracts, and interfaces.
- Run side-by-side evaluations of OGAI and Ovid.com outputs against the gold-standard datasets to inform consolidation decisions.
- Develop a phased plan for replacing or supplementing OGAI components, with sequencing, dependencies, risks, and validation checkpoints.
Qualifications
Clinical research and biostatistics
- Current enrollment in a medical degree program.
- Working knowledge of clinical trial design, biostatistics (effect measures, confidence intervals, meta-analysis), and evidence-based medicine frameworks (GRADE, PRISMA, Cochrane risk-of-bias tools).
- Preferred: experience with data extraction or critical appraisal for systematic reviews.
Systems engineering
- Ability to document multi-stage workflows as process and data-flow maps, interface specifications, and dependency analyses.
- Proficiency in Python (FastAPI, agentic pipeline design, XML and PDF parsing, pytest) and TypeScript/JavaScript (React/Next.js).
- Preferred: experience building LLM-based or agentic extraction and verification pipelines for medical literature.
Our Interview Practices
To maintain a fair and genuine hiring process, we kindly ask that all candidates participate in interviews without the assistance of AI tools or external prompts. Our interview process is designed to assess your individual skills, experiences, and communication style. We value authenticity and want to ensure we’re getting to know you—not a digital assistant. To help maintain this integrity, we ask to remove virtual backgrounds and include in-person interviews in our hiring process. Please note that use of AI-generated responses or third-party support during interviews will be grounds for disqualification from the recruitment process.
Applicants may be required to appear onsite at a Wolters Kluwer office as part of the recruitment process.