Sonali Shendge

Final-year Artificial Intelligence and Data Science engineering student

Pune, Maharashtra 80 · Excellent

About

Final-year Artificial Intelligence and Data Science engineering student with hands-on internship experience building predictive maintenance models at Tata Motors. Skilled in Python, machine learning fundamentals, and data visualization, with a strong foundation in data structures, algorithms, and object-oriented programming. Known for analytical thinking, attention to detail, and delivering reliable, well-tested solutions under deadlines.

Skills & Expertise (26)

Python Advanced

8.0/10

Years Exp

Pandas Advanced

7.5/10

Years Exp

scikit-learn Advanced

7.5/10

Years Exp

Research-driven approach Advanced

7.0/10

Years Exp

Collaborative Teamwork Advanced

7.0/10

Years Exp

Clear Communication Advanced

7.0/10

Years Exp

Attention to Detail Advanced

7.0/10

Years Exp

Analytical Problem-Solving Advanced

7.0/10

Years Exp

Machine Learning fundamentals Advanced

7.0/10

Years Exp

NumPy Advanced

7.0/10

Years Exp

Matplotlib Advanced

7.0/10

Years Exp

SQL Intermediate

6.5/10

Years Exp

Seaborn Intermediate

6.5/10

Years Exp

Computer Vision Intermediate

6.0/10

Years Exp

Object-Oriented Programming Intermediate

6.0/10

Data Structures & Algorithms Intermediate

6.0/10

C++ Intermediate

5.5/10

React YOLOv8 Retrieval-Augmented Generation Flask FastAPI FAISS LangChain Hugging Face OpenCV

Work Experience

Data Science Intern — Predictive Maintenance

Tata Motors Ltd.

Present - Present

Built a predictive maintenance model to forecast blower failures in advance by analyzing sensor data (temperature, pressure, vibration) from blower systems, supporting proactive maintenance planning. Cleaned, processed, and analyzed multivariate sensor datasets using Python and Pandas to identify early failure indicators and reduce noise in raw readings. Applied Scikit-learn to train and evaluate machine learning models, improving the reliability of failure predictions. Created visual reports using Matplotlib and Seaborn to communicate trends and model insights to stakeholders. Consolidated findings in Excel for cross-functional review by maintenance and engineering teams.