Research Data Analyst (SOM-Oncology)

Johns Hopkins UniversityBaltimore, MarylandOn-siteFull-timeMid level, 2–5 yearsListed 4 hours ago

Apply now

About this role

We are seeking a Research Data Analyst who will provide data analysis and related activities for various types of research projects and studies. The Research Data Analyst will contribute to ongoing development, maintenance, and use of a research data pipeline that collects and analyzes data.

The Bloomberg-Kimmel Institute for Cancer Immunotherapy (BKI) is recruiting an individual to design, build and deploy artificial intelligence (AI) agents that organize and manage BKI research data, convert our established research analyses into reusable agents, analyze publicly available data, support the development of a pan-cancer atlas, and accelerate scientific discovery. In this role, AI agents are software systems built on large language models (LLMs) and other machine learning methods that can use computational tools, query databases, run analysis pipelines, and summarize results under human oversight. This person will lead these efforts from data ingestion, pre-processing, and curation through analysis, interpretation and delivery of results to BKI investigators.

The candidate will work with BKI investigators to develop data and analysis plans that address biological and clinical hypotheses, and will translate these plans into AI agent workflows that are accurate, reproducible, and secure. The candidate will interact daily with other data analysts, as well as immunologists, genomics experts, and clinicians. This position requires collaboration with clinical and scientific investigators in research/study design, data analysis plans, algorithm and software development, grant applications, and preparation of presentations and publications. The candidate should work independently and in collaboration with faculty to solve problems posed by BKI investigators along the study design, data generation, collection, and management process, and will interact with bioinformatics experts, biostatisticians, software developers, computational scientists, and health informatics experts, as well as postdoctoral fellows from the Sidney Kimmel Comprehensive Cancer Center and the Bloomberg School of Public Health, on our immunogenomic data mining initiatives, with the goal of developing innovative AI-driven methods to integrate, analyze, and interpret data generated across BKI.

Specific Duties & Responsibilities

- Collect data and generate reports and models.
- Run models, analyze model results, and prepare reports on the analysis.
- Conduct analyses in support of the assigned research project or study.
- Conduct statistical analyses using standard and statistical software packages.
- Design and prepare tables to illustrate analytic findings.
- Manage or contribute to entry of data in the assigned database.
- May engage in other research related responsibilities.

In addition to the duties above

- Design, develop, deploy, and maintain AI agents (LLM-based systems that use software tools, databases, and analysis pipelines) to support BKI data management, reusable research analyses, the pan-cancer atlas, and scientific discovery.
- Lead data management, including determining type and format of data, metadata standards, and types of documentation, considering privacy, confidentiality, and other ethical issues.
- Build AI agents that automate data ingestion, pre-processing, cleaning, annotation, and quality control, including coding missing data, flagging or correcting miscoded data, harmonizing variables across studies, and summarizing data with descriptive statistics.
- Convert established BKI research analyses and pipelines into reusable AI agents, so that analyses can be re-run on new data consistently and on demand rather than repeated manually, with documented methods and version-controlled code.
- Develop and maintain a searchable data catalog and metadata repository, and AI agents that help investigators locate, retrieve, and request data; share data with BKI investigators and collaborators in accordance with approved data use and sharing agreements.
- Other duties as assigned.

Minimum Qualifications

- Bachelor's Degree in related discipline.
- Three years of related experience.
- Additional education may substitute for required experience, to the extent permitted by the JHU equivalency formula.

Preferred Qualifications

- Experience with computers and servers and knowledge of Linux/UNIX as well as other common operating systems such as Mac OS and Windows is necessary.
- Experience with high-performance computing (HPC) clusters, GPU resources, and secure cloud computing environments.
- Experience with server configuration, containerization (e.g., Docker, Singularity/Apptainer), and troubleshooting.
- Ability to use LLM application programming interfaces (APIs), AI-assisted development tools, and web-based scholarly search engines and databases.
- Proficiency in Python is required; proficiency in R is preferred.
- Hands-on experience with LLM APIs and agent development frameworks or protocols (e.g., LangGraph, LlamaIndex, Model Context Protocol, or similar).
- Knowledge of retrieval-augmented generation, vector databases, prompt design, and methods for evaluating LLM outputs.
- Experience with relational and/or NoSQL databases (e.g., SQL), data modeling, metadata standards, and FAIR data principles.
- Experience building reproducible pipelines using workflow managers (e.g., Nextflow, Snakemake) and containers.
- Proficiency with genomic data, tools, and databases, and familiarity with common computational biology tools and software packages, such as Bioconductor.
- Coursework or work experience covering topics in statistics, machine learning, molecular biology, genetics, and script-level programming.
- Knowledge of data storage, security, and privacy requirements for research and clinical data (e.g., HIPAA), and of responsible AI practices.
- Experience with experimental design principles and reproducible research principles.
- Experience developing web applications, dashboards, or user interfaces (e.g., Shiny, Streamlit) is preferred.
- Experience with large-scale public cancer datasets (e.g., TCGA) or building integrated multi-omic data resources is preferred.
- Familiarity with T cell receptor immunogenomics, cancer immunology, and immunotherapy is preferred.

Classified Title: Research Data Analyst  
Role/Level/Range: ACRP/04/MC  
Starting Salary Range: $49,200 - $86,200 Annually ($67,650 targeted; Commensurate w/exp.) 
Employee group: Full Time 
Schedule: Mon - Fri / 8:30a - 5p 
FLSA Status: Exempt 
Location: School of Medicine Campus  
Department name: SOM Onc Cancer Immunology Lab Research  
Personnel area: School of Medicine