• Learn about Viaduct’s history and mission • Get to know every team member • Set up your development environment • Understand Viaduct’s data pipelines and data science workflow • Learn about our current partners, their biggest needs, and the gaps they're looking for us to fill • Present your first deliverables internally • Scope-out and propose improvements to our products • Deploy improvements to our ML/Agentic pipelines • Present your work at our weekly team meetings • Be a thought leader on the data science team • Deploy world-class DS-based products and services • Collaborate with engineers on improvements to data science tooling • Present your models and relevant metrics to stakeholders

• Develop, validate, and maintain SDTM and ADaM datasets in R — using admiral and the broader pharmaverse — following CDISC standards. • Generate Tables, Listings, and Figures (TLFs) in R or SAS as required by study needs. • Perform Pinnacle21 validation, resolve findings, and refine specifications to ensure CDISC compliance and submission readiness. • Write efficient, reproducible, well-structured R code for clinical data analysis and reporting. • Contribute to open-source and internal tooling — including R Shiny / teal modules, R packages, SAS macros, and Python utilities — used by clinical programming, data management, and biostatistics teams. • Partner with statisticians, data managers, and clinical teams to translate programming requirements into reliable deliverables. • Perform QC, reconcile data issues, and ensure outputs meet regulatory expectations (e.g., FDA, EMA). • Support automation, pipeline development, and version-controlled workflows. • Use SAS for legacy studies or where SAS support is needed.

• Shape the data science roadmap: Identify measurement, audience, and AI capabilities that create value in each specialty market, and build a function that scales with the business. • Build causal lift measurement: Own the framework that demonstrates how HCP engagement drives real-world prescribing change — matched and synthetic controls, lookalike populations, methodologies defensible to pharmaceutical medical affairs and legal, and repeatable across therapeutic areas. • Build decisioning and personalization systems: Develop next-best-action, recommendation, and audience intelligence models that personalize the HCP experience and identify high-value audiences for sponsor targeting at scale. • Apply LLMs and generative AI across the workflow: Use them for structured extraction, feature engineering, insight generation, and HCP profile enrichment — wherever they cut time-to-insight without compromising rigor. • Translate findings into commercial products: Turn model outputs into sponsor-facing measurement reports, audience intelligence packages, and ROI dashboards, and present methodology directly to pharmaceutical medical affairs and commercial teams. • Own the ML platform layer: Feature engineering, experiment tracking, model registry, A/B and holdout frameworks, and production monitoring on the company's cloud and data warehouse stack.

• Join us in redefining what it means to work for a CRO. • Work closely with the multidisciplinary project team across the life cycle of the project to ensure data management is thoughtfully planned and delivered in a consistent, timely, and high quality manner. • Key contributor to project success through development and utilization of innovative tools to help automate manual tasks and identify data trends in a timely fashion. • Constant collaboration with project peers, particularly biostatisticians, statistical programmers, and clinical operations personnel. • Independently perform and oversee completion of data management tasks to ensure clinical database design supports project outcomes. • Proactively clean clinical trial data and mitigate risks. • Effectively communicate data-related decisions to sponsors and ensure data management activities follow all applicable standards and project-specific procedures.