Role Overview As a Data Scientist / Research Scientist, you will work on generating cohorts, and developing and validating machine learning models using EHR and clinical datasets. You will be responsible for data preprocessing, exploratory analysis, feature engineering, model development, and documentation of your findings. You’ll collaborate closely with domain experts, engineers, and stakeholders to deliver impactful AI solutions for disease prediction and personalized medicine. Key Responsibilities Execute end-to-end data science projects involving clinical data. Process and analyze complex datasets, including EHR and other real-world data sources. Develop predictive models using machine learning frameworks (e.g., BERT, CNN, etc.). Conduct exploratory data analysis and statistical hypothesis testing. Communicate findings via well-documented code, reports, and presentations. Collaborate with cross-functional teams, including clinicians, engineers, and product managers. Stay up-to-date with advances in machine learning, healthcare AI, and relevant research. Required Qualifications PhD or a Master’s degree (with 2–3 years of relevant experience) in Data Science, Biological Sciences, Computational Biology, or a related discipline. Candidates with a degree in Computer Science and demonstrated experience working with biological or clinical data are also encouraged to apply. Strong proficiency in Python, especially for data analysis (e.g., pandas, PyTorch, matplotlib, sci-kit-learn). Experience working with biological, clinical, or healthcare-related datasets in academia or industry. Solid understanding of statistical concepts and ability to apply them practically. Strong communication skills with an ability to document and explain technical work clearly. Preferred Qualifications (Nice to Have) Hands-on experience working with real-world or EHR data (structured/unstructured). Published or contributed to academic/industry research projects. Demonstrated use of programming/coding in research or work projects (GitHub, papers, or project links). Familiarity with healthcare data standards such as ICD, CPT, LOINC, HL7, or FHIR. Experience with ML pipelines and tools like scikit-learn, TensorFlow, PyTorch, or similar. Experience with Git or other version control systems. Show more Show less