Hi, my name is
Sree Vidya Cheekuri.
I'm a Data Scientist and Machine Learning Engineer specializing in computer vision and NLP. I transform complex data into actionable insights and build robust AI-driven solutions.
About Me
A passionate Data Scientist and ML Engineer currently pursuing a Master's degree at the University of Houston. I build robust predictive models and AI-driven solutions, transforming complex data into actionable insights. My experience spans academic research in computer vision and NLP to developing full-stack applications.
I've always been fascinated by the stories hidden within data. For me, a spreadsheet is a mystery novel, and a neural network is the key to unlocking it. I thrive on bridging the gap between intricate theory and real-world, high-impact applications.
Beyond the code, I'm a collaborative team player who believes the best solutions come from diverse perspectives. I'm constantly exploring the latest advancements in AI and am excited to apply my skills to a challenging role where I can contribute to cutting-edge projects and continue to grow as an engineer.
My Toolkit
Programming & Databases
Data Science Libraries
AI & ML Frameworks
AI Specializations
Methods & Foundations
Tools, Platforms & Visualization
Where I've Worked
Machine Learning Research Intern @ University of Houston
Nov 2024 – Present
- Applying ML to material science, building predictive models for concrete durability to tackle corrosion and leaching.
- Achieved 92% model accuracy while cutting traditional testing times in half through ensemble learning and neural networks.
- Directly contributing to research in sustainable infrastructure development.
AI/ML Research Intern @ Deakin University, Australia
Mar 2023 – Jul 2023
- Developed a full web service to forecast tourism demand, achieving 85% predictive accuracy using ARIMA and LSTM models.
- Engineered the entire backend pipeline with Flask and SQL, delivering real-time forecasts via a RESTful API.
Full Stack Web Developer @ Solar Secure Solutions
May 2022 – Jul 2022
- Engineered and deployed interactive web modules for client-facing platforms using Python, JavaScript, and HTML/CSS.
- Improved user navigation and interactivity, leading to a 25% increase in user engagement.
Things I've Built
6D Pose Estimation for Robotic Grasping
I tackled the challenge of teaching a robot to see and grasp objects in 3D space from a single image.
- Architected an end-to-end vision system using a PyTorch and ResNet50 backbone.
- Engineered the model to regress an object's precise 3D rotation and translation.
- Achieved near-perfect spatial awareness with a validation MSE of less than 0.0002.
Video Action Recognition
This project focused on teaching a machine to understand diverse human actions in raw video clips.
- Designed a deep learning model combining a CNN for spatial features with an LSTM for temporal analysis.
- Processed and trained the model on the UCF101 dataset, which contains 101 action categories.
- Achieved 88% accuracy in classifying actions from 16-frame video sequences.
Generative Storytelling with AI
I created a multimodal AI system capable of turning simple text prompts into fully animated videos.
- Utilized Large Language Models (LLMs) to interpret the narrative and scene structure from text.
- Employed Generative Adversarial Networks (GANs) to create the corresponding visual scenes.
- Achieved a 95% scene-text alignment, creating a powerful tool for automated content creation.
Concrete Strength Prediction
This project provides a robust tool for construction quality control by accurately predicting concrete strength.
- Built a meta-learning ensemble of stratified CatBoost models.
- Leveraged domain-informed feature engineering to achieve high predictive accuracy.
Chloride Corrosion Prediction
An ensemble ML pipeline designed to predict chloride-induced corrosion in reinforced concrete.
- Utilized a combination of MLP and XGBoost models for high-accuracy predictions.
- Provides a powerful predictive tool for assessing long-term infrastructure durability.
Assistive Tech for the Visually Impaired
I developed a tool to help visually impaired individuals perceive emotional context in conversations.
- Built a MATLAB-based system using Local Binary Patterns and Neural Networks for face detection.
- The model recognizes emotions with 93% accuracy and provides real-time voice feedback to the user.
Publications
What's Next?
I'm actively seeking new opportunities and collaborations where I can contribute to innovative, data-driven products.
My inbox is always open, whether you have a question or just want to say hi.
Feel free to reach out — I'm happy to chat about AI, tech, or anything in between!