Rahul Kaushik

RAHUL KAUSHIK Data Scientist | ML & AI Engineer | CAE Engineer Profile Summary Multidisciplinary engineer with expertise in physics-based modeling, simulation, and design validation of complex engineering systems (FEA, CFD, vibration & suspension, thermal–structural). Skilled in data-driven analytics, machine learning and predictive modeling for actionable insights. Experienced in delivering scalable, interpretable solutions across engineering and data domains. Skills Programming & Data: Python (NumPy, Pandas, Matplotlib, Seaborn), SQL, MongoDB, Excel, Git, Jupyter Notebook, EDA, Statistics, Time-Series Forecasting (ARIMA/SARIMA/ARIMAX/SARIMAX) ML & AI: Supervised/Unsupervised Learning, Regression, Classification, Clustering, Ensemble Methods, PCA, Hyperparameter Tuning, Deep Learning (ANN, CNN, RNN, LSTM, GRU, AutoEncoders, GANs), NLP (BERT, T5, Word2Vec, TF-IDF), Generative AI (DALL-E, MidJourney, OpenAI GPT, Hugging Face, LangChain) Deployment & Big Data: AWS, Azure, Flask, Streamlit, Docker, Kubernetes, Hadoop, Spark, Hive, MLOps, Model Deployment & Monitoring Visualization & BI: Tableau, Power BI, Matplotlib, Seaborn, Dashboarding Engineering: CAE, FEA, CFD, CAM, SolidWorks, Abaqus, Ansys, MasterCam, Nuclear Engineering, Reactor Physics, Monte Carlo Simulations, Particle Accelerator Physics Professional Experience Scientific Officer | Raja Ramanna Centre for Advanced Technology| 2022 - Present | Indore, India - Interferometer Lock Loss Prediction: Developed a predictive model using seismic channel time-series data, applying DMAT (Digital Matrix / Dynamic Matrix Analysis Tool) -based time-history learning and transfer-learning CNNs ResNet50/EfficientNet) to accurately predict lock-loss events. - Development of Control System and Machine Learning Model for Optic Steering: Led the design and implementation of a precision OSEM-based control system, analyzed 10,000+ actuator-displacement data points and developed predictive ML models (KNN, Random Forest, AdaBoost) achieving ±100 micrometers positioning accuracy, enhancing system responsiveness and improving model prediction accuracy by 25%. - Development of Single-Stage Suspension for End Station: Modeled single-stage suspension in Mathematica incorporating flexural corrections, thermoelastic damping, and dissipation dilution; validated CAD designs and experiments, achieving first six modes below 80 Hz and improving low-frequency vibration isolation by 15%. - Development of Triple-Stage Suspension for Beam Splitter: Mathematically modeled three-stage suspension in Mathematica with transfer functions for low-frequency isolation; addressed OSEM actuation constraints, achieving first 18 modes below 60 Hz and enhancing seismic isolation by 20%, enabling control strategy development. - Development of Lightweight Back-Pocketed Mirror using Diffusion Bonding: Designed CAD and FEA-optimized 500 mm mirror with mass-reducing pockets, reducing weight from 50 kg to 10.5 kg while limiting deflection to 163 nm (from 544 nm), improving rigidity by 70%, and establishing diffusion bonding parameters for manufacturable optical components. - Development of Semi-Continuous Production Facility for Optical Glass: Led the design and thermal optimization of a platinum-based optical glass production system using CAD and transient/steady-state thermal analysis, ensuring optical homogeneity of 10^-4; optimized power input, insulation thickness and melt flow rate to maintain uniform temperature, prevent bubble entrapment and significantly improve energy efficiency and glass quality. - Quality Prediction of Produced Optical Glass: Developed a machine-learning–based quality prediction framework for optical glass by correlating process parameters with optical homogeneity; applied Random Forest regression and PCAbased dimensionality reduction, achieving improved prediction accuracy and a 20% reduction in RMSE for reliable optical glass performance assessment. Scientific Officer | Bhabha Atomic Research Centre |2015 - 2022 | Mumbai, India - Anomaly Diagnosis of Steam Turbine: Led development of an ML-based early fault detection system for reactor steam - - - turbines by gathering condition monitoring data, applying PCA for feature reduction, K-Means for fault clustering, SMOTE for class balancing and an XGBoost multi-classifier, improving prediction accuracy and reliability by 25%. Effect of Polyurea Coating on Impact Resistance of Steel: Investigated and optimized polyurea-coated steel under impact loading by extracting viscoelastic properties for Abaqus modeling, performing analytical and FE simulations and validating results experimentally, identifying optimal coating thickness for maximum impact resistance. CAD Design and Structural–Thermal FEA of Hazardous Material Transportation Casks: Designed Type-B(M) and Type-C hazardous material transportation casks and performed dynamic explicit FEA for normal (9 m/s) and accidental (90 m/s) impact scenarios across multiple orientations, along with transient and steady-state thermal analyses at 800 °C for 30 minutes, to identify critical load cases and verify structural integrity under regulatory conditions. Radiation Safety Analysis and Qualification Testing of Transportation Casks: Conducted Monte Carlo simulations to evaluate Transport Index (TI) and Criticality Safety Index (CSI), and executed qualification testing under Normal and Accidental Conditions as per IAEA SSR-6 guidelines to validate radiation shielding performance, criticality safety margins and overall design readiness for operational deployment. Data Science Projects - - - - Customer Segmentation & RFM Analysis: Cleaned 100k+ transactions, computed RFM metrics for 50k+ customers, segmented into Platinum/Gold/Silver/Bronze tiers using quantiles and delivered treemap-based insights that improved targeted engagement and retention strategy effectiveness. Credit Risk Analysis & Predictive Modeling: Engineered financial and behavioral features from account, payment, delinquency, and enquiry history; handled missing data, multicollinearity, and class imbalance (SMOTE) and built tuned RF, XGBoost and ANN models achieving ~15% accuracy improvement. Employee Attrition Prediction: Performed EDA on 10k+ employee records, built a robust preprocessing and modeling pipeline with SMOTE and Random Forest and improved attrition prediction accuracy by ~15% through hyperparameter tuning. Insurance Claim Amount Prediction: Processed 100k+ insurance records, applied statistical feature selection, PCA, and ensemble regressors and optimized Gradient Boosting to achieve ~20% R² improvement and ~10% MSE reduction. Oil Well Production Forecasting: Engineered geological and depth-based features, reduced feature space by ~30% using statistical tests and compared multiple regression models to achieve ~15% MSE reduction in daily oil production prediction. Telecom Customer Churn Prediction: Conducted EDA on 50k+ records, applied feature selection and SMOTE and trained RF, XGBoost, Logistic Regression and LightGBM models, achieving ~20% accuracy and ~15% precision improvement. Web Scraping & COVID-19 Data Analysis: Scraped real-time data from 10+ sources, cleaned and transformed multi-source datasets and built interactive Plotly dashboards for trend analysis and real-time decision support. AI-Based Sentiment Analysis & Recommendation: Processed 50k+ text records, applied TF-IDF and XGBoost, and achieved ~85–90% accuracy in sentiment and mental health outcome classification for cancer survivors and caregivers. Stock Market Time Series Forecasting: Cleaned and decomposed 100k+ stock price records, ensured stationarity and built ARIMA and Prophet models delivering 85%+ forecasting accuracy for 1 - 3 month horizons. Twitter Sentiment Analysis (NLP): Analyzed 50k+ tweets using classical NLP, deep learning (LSTM/GRU) and transformer models (BERT/GPT), achieving up to 90%+ accuracy in sentiment classification. Education - Online Master Certificate, Data Science & AI | Learnbay, Bangalore| 2022 — 2024 PG Diploma, Nuclear Science & Engineering| Bhabha Atomic Research Centre, Mumbai| 2014 — 2015 BE, Mechanical Engineering| Shri G S Institute of Technology & Science, Indore| 2010 — 2014 Accomplishments - Group Achieve Award| Enhanced Mixed Carbide Fuel Fabrication for FBTR & Transportation of Special Nuclear Materials| 2018 Group Achieve Award| Development of Transport Package Impact Dampener| 2017 Scholarship | Central Sector Scheme of Scholarship|- Certificates - Data Science and AI Certificate for Managers & Leaders | IBM Skills Network | 2024 - Deep Learning Fundamentals | IBM Skills Network | 2024 Machine Learning with Python | IBM Skills Network | 2024 Python 101 for Data Science | IBM Skills Network |2024 Hands on Training on Computational Fluid Dynamics | Indian Nuclear Society | 2019 Basic Radiological Safety & Regulatory Measures for Nuclear Facilities | BARC Safety Council Secretariat | 2018 Application of Numerical Heat Transfer to Industrial Problems | Indian Nuclear Society | 2017 Application of Finite Element Technique in Industrial Problem| Indian Nuclear Society | 2017 Design of Nuclear Pressure Vessel & Piping | Indian Nuclear Society | 2016 Executive Excellence Program | Dale Carnegie & Associates, Inc. | 2015