Home
About Me
As a Senior Machine Learning Engineer at American Airlines, I work in the schedule reliability team by predicting precise flight block times. My work reduces excess flight hours and supports reliable, high-utilization scheduling solutions. With over five years of AI/ML industry experience, I’ve delivered production-ready systems for forecasting, risk management, and personalized recommendations. Currently, I’m advancing my expertise through Stanford University’s Artificial Intelligence Professional Program.
I’m proficient in Python, TensorFlow, PyTorch, Databricks, PySpark, and cloud platforms like AWS and Google Cloud. I earned a Master’s in Computer Science (4.0 GPA) from UT Arlington, along with Graduate Diplomas in Deep Learning and Big Data. Previously, as a Graduate Teaching Assistant, I supported courses in Algorithms and Distributed Systems.
Passionate about innovation, I’m driven to push the limits of AI and data solutions in aviation and beyond.
Education
- Artificial Intelligence Professional Program, Stanford University
- CS224N: Natural Language Processing with Deep Learning
- CS234: Reinforcement Learning
- Master of Science in Computer Science, University of Texas at Arlington
- Key Courses: Advanced Machine Learning, Data Structures & Algorithms, Big Data, AI, Cloud Computing, Neural Networks
- Graduate Diploma in Deep Learning, University of Texas at Arlington
- Highlights: Neural Networks, Computer Vision, Data Analysis & Modeling Techniques
- B.Tech in Electronics & Communication Engineering, K L University
Professional Experience
- Sr Machine Learning Engineer, American Airlines
- Software Engineer - Machine Learning, Trustt
- Data Scientist, Tracxn
- Applied AI/ML Analyst, Charles Schwab
- Machine Learning Research Intern, Qutrix Solutions
- Machine Learning Intern, Electronics Corporation of India Limited (ECIL)
Research Papers
- A Bidirectional People Counting Algorithm in Crowded Areas Arxiv Paper
Proposed and implemented a new algorithm to count the people in crowded areas and achieved an accuracy of 96%. - A Deep Learning Approach to Video Anomaly Detection using Convolutional Autoencoders Arxiv Paper
Proposed an algorithm for detecting anomalies in videos using convolutional autoencoders and decoders on the UCSD dataset (99%).
Teaching
Teaching Assistant for the following courses at UTA:
- CSE5311: Design and Analysis of Algorithms
- CSE3313: Theory of Computation
- CSE5306: Distributed Systems
Certifications
Skills
Python 
TensorFlow 
PyTorch 
FastAPI 
Flask 
LangChain 
Spark 
MySQL 
MongoDB 
Streamlit 
Kafka 
AWS 
Google Cloud 
NumPy 
Pandas 
Docker 
Kubernetes 
Git Blog Posts
- 06/09/2023 Introduction to Convolutional Neural Networks.
- 10/15/2022 A social Network Portal for Lease Transfer.
- 10/01/2022 A Efficient Portal For Course Registraion System.