Data Science with 1+ years in Predictive Modeling & ML Pipelines
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Data Scientist and Software Engineer with a published research specialization in predictive modeling, high-dimensional statistical analysis, and production-grade ML pipeline design. Conference presenter at NEleX-2026 with a peer-reviewed machine learning publication. Proven track record of engineering architectures achieving a 93% AUC-ROC, deploying high-throughput model endpoints handling 1,000+ daily inference requests, and optimizing data vectorization for complex workflows. Expert Python programmer combining deep algorithmic knowledge with robust deployment strategies for high-scale consumer applications.
Vellore Institute of Technology (VIT)
M.Tech Integrated · Software Engineering
August 1, 2022 – May 1, 2026
Andhra Pradesh State Board
Senior Secondary School
N/A – Present
Andhra Pradesh State Board
Secondary School
N/A – Present
Open-Source Portfolio
Independent Data Scientist
January 1, 2025 – March 1, 2025
India
VIT Vellore
Lead Data Engineer & Researcher
August 1, 2024 – December 1, 2024
Vellore, Tamil Nadu, India
Open-Source Portfolio
Data Pipeline Engineer
March 1, 2024 – June 1, 2024
India
Behavioral Predictive Analytics & Customer Churn Engine
January 1, 2025 – March 1, 2025
Engineered a robust statistical predictive model utilizing 15+ complex user behavioral feature vectors to isolate churn risk indicators, achieving an 89% validation accuracy and a 0.91 F1-score. Conducted extensive data preprocessing, missing data imputation, and synthetic oversampling to alleviate class imbalances, ensuring un-biased model classification metrics. Wrapped the model pipeline into a high-throughput, low-latency microservice endpoint via FastAPI, reliably serving 1,000+ daily inferencing evaluations with sub-200ms processing times on Azure Cloud.
High-Dimensional Multi-Omics Predictive Framework (Published Research)
August 1, 2024 – December 1, 2024
Developed an end-to-end predictive classification pipeline processing over 100K+ high-dimensional data points, achieving a 93% AUC-ROC and 87% Micro-F1 Score via an optimized XGBoost and Random Forest ensemble strategy. Implemented statistical feature selection techniques and variance thresholds to execute a 40% dimensionality reduction, preserving model variance while significantly shrinking training convergence time. Productionalized the predictive architecture by deploying the ensemble model as a serverless microservice via AWS Lambda, minimizing cold-start latency to under 1 second and reducing cloud computational infrastructure costs by 35%.
Vectorized Analytics Pipeline & Public Health Engine
March 1, 2024 – June 1, 2024
Architected an automated ETL data orchestration engine in Python and SQL to ingest, clean, and map 100K+ records, using automated continuous integration jobs to ensure a 99% structural data integrity rating. Engineered 7 distinct interactive data exploration platforms utilizing Plotly; accelerated data manipulation runtimes by 60% (reducing latency from 8s to 2s) by structuring vectorized array operations over scalar loops.
SQL Gold Level Certification
HackerRank
June 1, 2026 – Present
Data Structures & Algorithms in Python Certification
GeeksforGeeks
June 1, 2026 – Present
Microsoft Azure Data Fundamentals (DP-900)
Microsoft
June 1, 2026 – Present
Cultural Fit Analysis
The candidate demonstrates a strong cultural fit for a data science role, particularly one that values innovation, practical application, and continuous improvement. Their academic research, personal projects, and certifications showcase a broad interest and commitment to the field. The diversity of projects, from academic research to open-source contributions, indicates adaptability and a willingness to tackle different problem domains. The focus on optimizing performance and cost aligns with business-oriented values.
Soft Skills & Operational Fit
The candidate's project descriptions highlight a proactive and results-oriented approach, focusing on optimizing performance, reducing costs, and ensuring high data integrity. Their involvement in published research and open-source projects suggests a strong drive for continuous learning and contribution. The emphasis on TDD and CI/CD indicates an understanding of robust software development practices, which is crucial for operational fit in a senior role.