Research Assistant - Radiation Oncology

The Research Assistant works within the clinical research program and supports the research team in the overall conduct of clinical trials using Good Clinical Practice under the auspices of the Principal Investigator(s) and the DF/HCC Clinical Trials Office and/or MGB Institutional Review Board (IRB). The Research Assistant (RA) will be responsible for the primary data collection and management of patient clinical information as it pertains to participation in clinical trials.

We are looking for a highly organized candidate with great attention to detail for the position of data coordinator. RAs are responsible for data entry, cleaning, transformations, and data analyses as requested by analysts or senior management. Additionally, RAs will need to adhere to legal and regulatory standards, among other duties, requiring them to maintain excellent organizational skills and data integrity.

For this role, the Research Assistant will support work from a faculty member focused on application of artificial intelligence and data science to optimize the care of cancer patients with a focus on lung cancer. The faculty member(s) is committed to training and inspiring the next generation of health care leaders and clinicians, working on important clinical and healthcare issues, and utilizing new technologies like AI to improve outcomes and reduce toxicity.

We seek an energetic and organized, detail-oriented individual to assist with a portfolio of data science research projects in the Department of Radiation Oncology. Candidates with backgrounds in data science and informatics and/or experience with programming languages are preferred. Because the team builds and maintains its own AI models, data pipelines, and research web applications in-house, this role combines clinical research coordination with hands‑on data science and software engineering.

Candidates who are comfortable working in a Linux environment, using version control, containerizing and deploying applications, and applying best software engineering and data science practices are especially encouraged to apply. Prior exposure to clinical/healthcare data, electronic health records, and Good Clinical Practice (GCP) is an asset.

1. The successful candidate will be able to work with faculty and research team members to accomplish, data compilation, data management, statistical programming, and other research related duties.

2. May assist the study start-up process from receipt of protocols through the Scientific Review Committee and IRB submissions, and site activation activities.

3. May assist coordinating and management of clinical trials, interact with study participants as directed/required by the protocol and/or study team.

4. These duties and responsibilities include but are not limited to:

• Extracting data from electronic health records
• Management of a large lung cancer patient database including regulatory considerations
• Compiling and cleaning data from various sources as well as assessing the data quality; routine data maintenance
• Statistical programming on large data sets (for example, analyzing data sets extracted from electronic health record databases)
• Analysis and validation of empirical results
• Participating in manuscript presentations with opportunities for co-authorship
• Producing charts and tables for manuscripts and presentations
• Analyzing pilot data to support the start-up of new projects
• Onboarding new research collaborators
• Querying and harmonizing data across multiple clinical, imaging, and research systems (e.g., the electronic health record, research data registries, and radiation‑oncology treatment‑planning systems)
• Developing and maintaining reproducible, version‑controlled data‑science pipelines and analysis code (e.g., using Git/Git Hub)
• Training, running, and validating deep‑learning models on GPU infrastructure, including models applied to medical imaging and digital biomarkers
• Building, maintaining, and deploying research web applications across development, staging, and production environments
• Containerizing applications and supporting deployment and release workflows
• Maintaining clinical trial regulatory…