Director, Oncology Evidence & Real-World Analytics

AstraZeneca; Cambridge (MA); Hybrid; USD 145,000 - 217,000; Full time

Benefits offered by this job

Health, dental, and vision coverage

Retirement programs

Paid time off

Job summary

AstraZeneca in Kendall Square/Cambridge is seeking a senior technical specialist in clinical intelligence and real‑world evidence to shape evidence that informs Phase 3 investments, trial design and patient access. You will build multimodal patient models and external control arms, translating complex data into decision‑ready insights for Hematology and oncology.

With a PhD or equivalent, 5+ years in evidence strategy and analytics, you will apply causal inference, machine learning, and

Qualifications

• Advanced degree (PhD or equivalent) in a quantitative discipline - epidemiology, biostatistics, computational biology, machine learning, health data science, or a related field.
• 5+ years of experience spanning both evidence strategy and real-world evidence and/or advanced analytics and data science.
• Strong methodological foundation in causal inference and observational study design, including propensity score methods, instrumental variables, target trial emulation, and comparative effectiveness research.
• Hands-on experience with machine learning and multimodal modeling, including supervised and unsupervised methods, deep learning for imaging or molecular data, and integration of heterogeneous data types into patient-level models.
• Experience building or contributing to external control arms, trial simulators, or prognostic models using real-world and/or clinical trial data.
• Understanding of regulatory and health technology assessment (HTA) evidence standards, with the ability to design analyses that meet the evidentiary bar for submissions and payer engagement.
• Proficiency in Python, R, and SQL, and familiarity with cloud-based analytics environments.

Responsibilities

• Evidence Gap Prioritization: Identify and prioritize evidence needs across the product lifecycle, including Phase 3 investment decisions, subpopulation discovery, and trial design.
• AI and Causal Inference Analytics: Apply machine learning and causal inference to deliver robust answers on patient stratification, external control arm construction, prognostic risk adjustment, and treatment effect heterogeneity.
• Multimodal Patient Models: Deliver and validate patient-level models that integrate clinical, genomic, imaging, and real-world data for deployment in clinical trials or routine care, with emphasis on reproducibility and rigorous validation.
• Decision-Ready Insights: Turn internal and competitor trial data, alongside real-world data, into clear insight on standard of care, patient pathways, benchmarking, and unmet need to sharpen development and access strategies.
• Platform Enablement: Work with platform and tooling teams to bring new tools, agents, and experimental approaches into evidence generation, and build Hematology-specific intelligence that persists within the Phase 3 Investment Decision Intelligence Foundation.
• Cross-Functional Collaboration: Connect strategic evidence needs with technical delivery, aligning outputs to development, regulatory, and access milestones; collaborate with Translational Science and Clinical Development to incorporate novel signals such as digital endpoints, pathology AI, and biomarker panels.

Skills

Policy & evidence strategy

Causal inference

Machine learning

Multimodal modeling

Python

R

SQL

Regulatory & HTA

Clinical data integration

Education

PhD or equivalent in a quantitative discipline

Tools

Python

R

SQL

Job description

AstraZeneca in Kendall Square/Cambridge is seeking a senior technical specialist in clinical intelligence and real‑world evidence to shape evidence that informs Phase 3 investments, trial design and patient access. You will build multimodal patient models and external control arms, translating complex data into decision‑ready insights for Hematology and oncology.

With a PhD or equivalent, 5+ years in evidence strategy and analytics, you will apply causal inference, machine learning, and