NAVEEN KUMAR GORRE

Berlin

Summary

Software Engineer with 3.5+ years of experience building and deploying predictive models and recommendation systems, achieving up to 18% RMSE reduction through advanced feature engineering and optimization techniques. Skilled in real-time anomaly detection using statistical methods, reducing issue resolution time. Proficient in streamlining analytics workflows, data visualization, and dashboard development for actionable insights and operational gains. Skilled in CI/CD automation (Jenkins, GitHub Actions, Docker, Kubernetes), Well-versed in in Python, TensorFlow, PyTorch, and AWS.

Work History

Machine Learning Engineer

TCS

01.2022 - 2024

Developed and deployed supervised learning models (XGBoost, Random Forest, GLMs) for time-series forecasting of product sales and booking patterns, leveraging feature selection (SHAP, RFE) and cross-validation to reduce RMSE by 18%.
Engineered a recommendation system (collaborative filtering + content-based) using gradient-boosted trees (XGBoost, LightGBM), achieving 74% precision-recall (F1-score) via hyperparameter optimization (Bayesian Optimization, GridSearchCV) and feature importance analysis.
Performed real-time anomaly detection and root-cause analysis on customer data pipelines using advanced statistical methods (Z-score, IQR, DBSCAN) to proactively identify and resolve system irregularities, reducing discrepancy resolution time by 14%.
Implemented CI/CD Pipeline(Jenkins, GitHub Actions) and version control practices using Git for seamless deployments across multi-tier environments (Dev/Test/Prod).

Junior Data scientist

TCS

01.2021 - 2022

Streamlined data analysis processes, reducing time spent on data cleaning by 25%.
Developed dashboards that provided actionable insights, resulting in a 8% increase in efficiency.
Managed databases and improved data retrieval times by 20%, enhancing overall team productivity.
Conducted in-depth analysis that informed strategic planning, helping increase bookings by 10%.

Education

Master of Science - Software Engineering

University of Europe

08.2025

Bachelor of Science -

Osmania University

01.2019

Skills

Python (Pandas, NumPy, Scikit-learn, TensorFlow,Pytorch,ML Flow),C,Linux
Tools & Frameworks: REST, Git, Docker, Kubernetes, Flask, Git Copilot, Fast API
Machine Learning, Deep learning, Transfer learning, Hugging Face
Data Visualization: Matplotlib, Seaborn, Tableau

Database & Cloud: MySQL, PostgreSQL, AWS
Generative AI (LLM), Langchain, Langraph
A/B Testing

Projects

AI-Driven Docker file Generator with Google Gemini 2.0 Flash

Used Google Gemini 2.0 Flash, a lightweight and high-performance Large Language Model (LLM), to automatically create optimized Dockerfile
Integrated with Google AI Studio, the tool dynamically generates containerization scripts tailored to Python languages and dependencies, streamlining DevOps workflows

Transformer-Based Mis information Detection Project (NLP, Deep Learning)

Developed an advanced fake news detection system leveraging state-of-the-art transformer architectures (BERT, RoBERTa, DistilRoBERTa, Electra) and implemented a stratified K-Fold ensemble framework for robust model evaluation and variance reduction.
Designed and executed a comprehensive NLP data pipeline: text normalization, advanced tokenization (WordPiece, BPE), subword processing, categorical encoding, and attention masking to maximize model compatibility and performance.
Delivered actionable insights on trade-offs between ensemble complexity and single-model optimization for NLP practitioners, challenging conventional ensemble superiority assumptions in transformer-based classification task

Accomplishments

Statistics and Machine Learning Specialization from John Hopkins University Coursera
PGDM Certification in Data Science IIBM Institute of Business Management

LANGUAGES

English - Advanced

German - Elementary

Timeline