Skip to main content
Rajeev Prasad

Rajeev Prasad

Data Scientist | Healthcare Analytics | SQL, Python, Machine Learning | Predictive Modeling, Statistical Analysis & Data Visualization | University of Michigan

Talent
Lexington, MAMember since June 15, 2026
SQLPythonXGBoostRetrieval-Augmented GenerationLangChainChromaDBBiomedical Literature RetrievalNLPPredictive ModelingHealthcare AnalyticsStatistical reportingData AnalysisStreamlitData Visualization
·

Hire this person

Send a job offer directly to this candidate

SQLPythonXGBoostRetrieval-Augmented GenerationLangChain

About

Data scientist and healthcare analytics professional with experience in clinical research, medical data analysis, predictive modeling, machine learning, and statistical reporting within regulated healthcare environments. Skilled in Python, SQL, data visualization, dashboard development, and translating complex healthcare and commercial data into actionable business insights for technical and executive stakeholders.

Experience

Lead Data Scientist (2025-10 – 2026-05)

  • Built a Retrieval-Augmented Generation (RAG) application for biomedical literature question-answering using PubMed abstracts focused on breast cancer biomarkers and machine learning
  • Developed an end-to-end NLP pipeline using Python, LangChain, OpenAI embeddings, and ChromaDB to retrieve semantically relevant biomedical literature for evidence-grounded responses
  • Designed a Streamlit-based interactive interface enabling natural language querying of biomedical research abstracts for translational and healthcare analytics use cases
  • Integrated retrieval pipelines with LLM-based response generation to reduce hallucination risk and improve contextual grounding in scientific literature
  • Applied concepts including embeddings, vector databases, semantic retrieval, and prompt orchestration for biomedical AI and healthcare knowledge discovery

Lead Data Scientist (2025-03 – 2025-09)

  • Designed and executed translational research workflows integrating multi-modal genomic (scRNA-seq) and clinical datasets (500K+ cells) to identify tumor-specific molecular signatures, generating reports and insights to support data-driven decision making.
  • Built scalable machine learning pipelines for tumor vs. normal classification (AUC = 0.89) using XGBoost and interpretable AI techniques, supporting biomarker discovery and disease characterization.
  • Applied SHAP-based model interpretability to validate biological relevance of key drivers (e.g., MYC, ERBB2, CCND1), aligning ML outputs with known cancer pathways
  • Performed differential expression and pathway-level analyses to identify clinically actionable oncogenes and therapeutic targets
  • Mapped 75+ genes to DGIdb, Open Targets, and clinical trial data, stratifying into FDA-approved, emerging, and underexplored targets to support translational insights
  • Developed UMAP, network, and matrix visualizations to communicate complex molecular findings to technical and non-technical stakeholders

Scientist/Sr. Ass. Scientist at Zoetis Inc./Pfizer Animal Health (2010-01 – 2022-10)

  • Led cross-functional project teams of 6–8 scientists and veterinarians, provided mentorship on data pipelines, experimental design, and assay validation; ensured delivery of studies on time and within budget (~$500K–$1M per program).
  • Developed and validated 20+ preclinical disease models using bacterial and viral pathogens, enabling robust evaluation of vaccine candidates and supporting 3+ licensure submissions.
  • Advanced multiple vaccine programs from discovery to licensure, authoring 25+ regulatory dossiers to support vaccine registrations across US, EU, China, and Brazil, reducing approval timelines by an estimated 15–20%.
  • Directed data integration and statistical analyses across 10+ multi-site clinical trials, ensuring reproducibility and regulatory compliance (GCP/GLP).
  • Directed clinical programs as Clinical Lead, managing 4–5 concurrent vaccine studies and supervising teams of 10–12 staff under USDA 9CFR, VICH, and USDA Memoranda guidelines.

Scientist III at Fort Dodge Animal Health (2008-12 – 2009-12)

  • Managed laboratory/clinical studies for the licensure of commercial poultry vaccines (bacterial and viral).

Education

Master of Applied Data Science in Applied Data Science – University of Michigan, School of Information (2023 – 2025-08)

Master of Science in Biomedical & Veterinary Sciences – Virginia Polytechnic Institute and State University (2006 – 2008-11)

Master of Veterinary Science in Animal Biotechnology – Indian Veterinary Research Institute (2002 – 2004-08)

Bachelor of Veterinary Science and Animal Husbandry in Veterinary Science and Animal Husbandry – WB University of Animal and Fishery Sciences (1998 – 2002-07)

Skills

Data ScientistHealthcare AnalyticsSQLPythonMachine LearningPredictive ModelingStatistical Analysis & Data VisualizationUniversity of Michigan

Reviews

Related