Open to opportunities

anil mali

@anilmali

Message

I build practical AI/ML systems for prediction, detection, and real-world automation.

India

Message

What I'm looking for

I'm seeking an AI/ML engineering role where I can build impactful, real-world machine learning and deep learning solutions while growing through hands-on product, data, and model-development work.

I've built AI applications including a multipurpose drone system for surveillance, agriculture monitoring, and emergency alerting, achieving 91% mAP detection accuracy with OpenCV and TensorFlow.

I also developed a Streamlit-based stock market prediction system using Scikit-learn, Pandas, NumPy, and LSTM time-series neural networks trained on more than 10 years of historical data. The application improved forecast accuracy by 18% over a baseline model.

During internships with FlyRank Corp. and NeuroFive Solutions, I engineered predictive-maintenance pipelines, preprocessing workflows, and foundational regression and classification models. My work improved model accuracy by 14%, reduced data-cleaning time by 30%, and achieved 88% accuracy on credit card fraud detection datasets.

I'm pursuing a B.E. in Artificial Intelligence & Data Science and enjoy applying Python, machine learning, deep learning, and data-driven experimentation to impactful real-world AI solutions.

Experience

Work history, roles, and key accomplishments

Machine Learning Engineering Intern

FlyRank Corp.

Jul 2026 - Sep 2026 (2 months)

Engineered machine learning pipelines for predictive maintenance analytics, improving model accuracy by 14% using Python, Scikit-learn, and Pandas. Implemented data preprocessing and feature engineering workflows on datasets of 50K+ rows, reducing data cleaning time by 30%.

Python scikit learn Pandas Optuna Cross Validation data preprocessing Feature Engineering

Machine Learning Fundamentals Intern

NeuroFive Solutions

Jul 2026 - Jul 2026 (0 months)

Developed foundational ML models (regression/classification) using Scikit-learn and Pandas, achieving 88% accuracy on credit card fraud detection datasets. Built and tested real-time ML project prototypes by applying Random Forests and Support Vector Machines, reducing error rate by 15%.

scikit learn Pandas Random Forest Classification regression