Vrinda Kore

Associate Engineer — Data Science and Predictive Analytics

Bangalore 2+ yrs exp 86 · Excellent

About

Data Scientist with 2 years of experience developing machine learning and statistical analytics solutions using large-scale operational datasets. Experienced across the end-to-end model development lifecycle, including exploratory data analysis, feature engineering, anomaly detection, time-series analysis, and predictive modeling. Proficient in Python, SQL, PySpark, and data-driven problem solving, with experience translating complex data into actionable business insights.

Skills & Expertise (23)

Python Advanced

8.1/10

Years Exp

PyTorch Intermediate

7.8/10

Years Exp

Exploratory data analysis Intermediate

7.8/10

Years Exp

Anomaly Detection Intermediate

7.8/10

Years Exp

Deep Learning Intermediate

7.8/10

Years Exp

Pandas Intermediate

7.6/10

Years Exp

Streamlit Intermediate

7.6/10

Years Exp

Jupyter Notebook Intermediate

7.6/10

Years Exp

SQL Intermediate

7.4/10

Years Exp

NumPy Intermediate

7.4/10

Years Exp

Feature Engineering Intermediate

7.0/10

Years Exp

Matplotlib Intermediate

7.0/10

Years Exp

Time-Series Analysis Intermediate

7.0/10

Years Exp

Statistical Modeling Intermediate

7.0/10

Years Exp

TensorFlow Intermediate

6.8/10

Years Exp

Power BI Intermediate

6.6/10

Years Exp

MySql Intermediate

6.6/10

Years Exp

VS Code Intermediate

6.4/10

Years Exp

Git Intermediate

6.4/10

Years Exp

PySpark Intermediate

6.0/10

Years Exp

OpenCV Intermediate

6.0/10

Years Exp

Prompt Engineering Intermediate

6.0/10

Years Exp

LLM Applications Intermediate

6.0/10

Years Exp

Work Experience

Associate Engineer – Aviation Digital Alliance Team

Collins Aerospace

Oct 2025 - Present

Contributing to predictive analytics and Prognostics & Health Management (PHM) under Digital Alliance, a global collaboration involving Airbus, Collins Aerospace, Delta Air Lines, and GE Aerospace focused on data-driven maintenance and operational reliability. Developed anomaly detection and alerting algorithms using operational records and maintenance data across multiple aircraft systems, enabling earlier identification of abnormal behavior. Designed a dynamic thresholding algorithm that generated entity-specific alert limits from historical operating behavior, improving anomaly detection performance by over 80% compared with conventional static thresholds while reducing false alerts. Performed exploratory data analysis, failure mode investigations, feature engineering, and statistical modeling on new datasets of 1 Hz data to identify behavioral trends, data quality issues, degradation patterns, and candidate predictive features. Currently working on developing a novel analytics solution for failure prediction and health monitoring of electro-mechanical systems in a220 electric brakes using operational and maintenance data.

Graduate Engineer Trainee – Data Analytics

Collins Aerospace

Jul 2024 - Sep 2025

Engineered an LLM-powered analytics chatbot using Streamlit, enabling users to query manufacturing and rework datasets through natural language and automatically generate SQL queries. Automated recurring SAP data extraction workflows using Python, reducing manual effort and improving data availability for operational reporting.

Intern

Collins Aerospace

Jan 2024 - Jun 2024

Created a Power BI dashboard using 10 years of flight operations data to analyze delay causes, cancellation trends, and operational performance for a commercial aircraft fleet. Prepared and validated datasets for analytics and predictive modeling applications, ensuring data quality and consistency across multiple sources.

Summer Intern

IITD-AIA Foundation for Smart Manufacturing

Jun 2023 - Aug 2023

Implemented a predictive maintenance solution for bearing Remaining Useful Life (RUL) estimation using time-series sensor data as part of Industry 4.0 and smart manufacturing initiatives. Conducted exploratory analysis, feature extraction, and data preparation on operational and vibration datasets in order to find patterns of degradation. Built deep learning models using PyTorch to estimate bearing health and predict remaining useful life. Evaluated model performance and analyzed degradation trends to support condition-based maintenance strategies.