Johnson Jeeva J.

AI Researcher

Tucson, Arizona, United States4 yrs 7 mos experience

Key Highlights

Achieved top 7% in Kaggle’s 30 Days of ML Challenge.
Delivered 100% data integrity and actionable insights using Power BI.
Designed and optimized ML models achieving 85% predictive performance.

Stackforce AI infers this person is a Data Science and Engineering professional with a focus on Healthcare and Manufacturing industries.

Contact

jacob@tennessee.edu LinkedIn

Skills

Core Skills

Machine LearningData ScienceHealthcareResearchData Engineering

Other Skills

Agile MethodologiesAirtableAmazon Web Services (AWS)Atlas.tiAzureBERT (Language Model)Billing ProcessBoosted TreesBudgetingBusiness AnalyticsClinical NLPCommunicationDEVSData CollectionData Ethics

About

• Currently pursuing an MS in Data Science at the University of Arizona, aiming to leverage advanced analytics to solve complex business problems. • Ex-Data Science Intern at the University of Tennessee’s Data Science Institute, developing machine learning models using Python and R (including regression trees, random forests, boosted trees, MARS and neural networks) in manufacturing industries. Supporting research with integration into JMP and assisting in analytical validation for real-world industrial applications. • Ex-Data Engineer with 2 years of experience, specializing in data ingestion, ETL processes and dashboard creation. • Delivered 100% data integrity and generated actionable insights using Power BI, driving key decisions for stakeholders. • Achieved top 7% in Kaggle’s 30 Days of ML Challenge. • Proven track record in leading data-driven financial strategies and enhancing operational efficiency in a fast-paced environment.

Experience

4 yrs 7 mos

Total Experience

2 yrs 3 mos

Average Tenure

Current Experience

Ut institute of agriculture

Data Science Intern

Jun 2025 – Aug 2025 · 2 mos · Knoxville, Tennessee, United States · Hybrid

Designed and optimized diverse ML models (Boosted Trees, XGBoost, MARS, Ridge/Lasso, Neural Nets) with cross-validation, achieving 85% predictive performance (R²) on sensor data.
Integrated Scikit-learn and TensorFlow pipelines into JMP and Minitab through custom scripts, enabling managers to run advanced ML models directly inside their existing statistical tools.
Containerized Machine Learning workflows and automated dependency management using JSL scripts, enabling reproducibility and scalable deployment across partner organizations with sensitive proprietary data.
Delivered 3-day workshop to 20+ industry managers, demonstrating ML applications in manufacturing and driving adoption of predictive analytics.

PythonRMachine LearningJMPMinitabBoosted Trees+4

University of arizona

Researcher - AI for Healthcare

Feb 2025 – Aug 2025 · 6 mos · Tucson, Arizona, United States · Hybrid

The research focuses on extracting patient care pathways from Electronic Health Records (EHRs), predicting outcomes using deep learning, and simulating treatment interventions using Digital Twin technology.
This research aims to:
Discover real-world diagnosis-to-treatment pathways using process mining techniques
Predict patient outcomes and next steps using advanced deep learning models (e.g., TransformEHR, PheW2P2V)
Simulate patient flows using DEVS-based Digital Twin environments (MS4ME)
Incorporate clinician feedback into iterative, expert-in-the-loop model refinement

Deep LearningProcess MiningDigital TwinTransformEHRPheW2P2VData Science+1

University of arizona college of medicine – tucson

Research Assistant

Jan 2025 – May 2025 · 4 mos · Arizona, United States

Managed interview data collection and qualitative analysis using Atlas.ti, focusing on barriers to fall prevention among older adults.
Developed patient education interventions using AI-enhanced tools, improving health literacy and reducing future complications.

Qualitative ResearchAtlas.tiResearch

Ltimindtree

2 roles

Data Engineer

Nov 2022 – Jul 2024 · 1 yr 8 mos

Led migration of 10+ production automations and chatbots for a global client, streamlining workflows and delivering 20–25% time savings and six-figure annual cost reduction.
Designed and deployed ETL pipelines to ingest and transform data from multiple sources into a datalake, serving as architect to ensure 99% data integrity and system reliability.
Developed Power BI dashboards on Azure for KPI dashboards and automation reporting, enabling managers to make data-driven decisions on SLA compliance and efficiency.
Maintained production pipelines and automations with ongoing monitoring, enhancements and bug fixes, improving data processing speed by 40% and enabling real-time business insights.

ETLPower BIAzureData IntegrityData ProcessingData Engineering

Graduate Engineering Trainee

Jul 2022 – Oct 2022 · 3 mos

Successfully completed a Big Data and Analytics training program, contributing to a top-performing project team.
Designed a data modeling and warehousing solution using Informatica, improving e-commerce data pipeline efficiency and storage optimization.

Data ModelingInformaticaData Engineering