Hey there, I'm Sanjana Ratan
AI undergrad aspiring to become an AI Engineer, passionate about building smart, real-world solutions using GenAI, data science, and cloud technologies.
☁️ Cloud-Based Solution for Residential Security and Efficiency
Built a serverless cloud system using AWS to automate visitor and vehicle entry tracking in gated communities. Used AWS Rekognition for OCR on vehicle plates, verified against a secure owner database in DynamoDB. Lambda functions handled real-time validation and event-triggered notifications via SNS. Added a mobile-accessible front-end interface to manage and approve visitors. Entire pipeline is scalable, cost-efficient, and integrated with security logs for audits. Improved gate efficiency and resident safety.
Tech Stack: AWS (Rekognition, Lambda, DynamoDB, SNS), Python, Cloud Architecture, Serverless Computing,
☁️ Cloud-Based Solution for Residential Security and Efficiency
Built a serverless cloud system using AWS to automate visitor and vehicle entry tracking in gated communities. Used AWS Rekognition for OCR on vehicle plates, verified against a secure owner database in DynamoDB. Lambda functions handled real-time validation and event-triggered notifications via SNS. Added a mobile-accessible front-end interface to manage and approve visitors. Entire pipeline is scalable, cost-efficient, and integrated with security logs for audits. Improved gate efficiency and resident safety.
Tech Stack: AWS (Rekognition, Lambda, DynamoDB, SNS), Python, Cloud Architecture, Serverless Computing,
☁️ Cloud-Based Solution for Residential Security and Efficiency
Built a serverless cloud system using AWS to automate visitor and vehicle entry tracking in gated communities. Used AWS Rekognition for OCR on vehicle plates, verified against a secure owner database in DynamoDB. Lambda functions handled real-time validation and event-triggered notifications via SNS. Added a mobile-accessible front-end interface to manage and approve visitors. Entire pipeline is scalable, cost-efficient, and integrated with security logs for audits. Improved gate efficiency and resident safety.
Tech Stack: AWS (Rekognition, Lambda, DynamoDB, SNS), Python, Cloud Architecture, Serverless Computing,
🎨 Realistic Product Visualization Using DreamBooth & Hugging Face
During my internship, I developed a generative AI pipeline to convert raw product samples into realistic, human-worn visuals for marketing and branding purposes. The workflow involved fine-tuning a Stable Diffusion model using DreamBooth with company-provided sample images. Guided prompts were designed to control visual attributes like pose, lighting, and context. This solution enabled the generation of high-fidelity synthetic visuals, eliminating the need for physical photoshoots and accelerating marketing asset production.
Tech Stack: Stable Diffusion, DreamBooth, Hugging Face Diffusers, Prompt Engineering, Python, Gradio UI, Image Augmentation
🎨 Realistic Product Visualization Using DreamBooth & Hugging Face
During my internship, I developed a generative AI pipeline to convert raw product samples into realistic, human-worn visuals for marketing and branding purposes. The workflow involved fine-tuning a Stable Diffusion model using DreamBooth with company-provided sample images. Guided prompts were designed to control visual attributes like pose, lighting, and context. This solution enabled the generation of high-fidelity synthetic visuals, eliminating the need for physical photoshoots and accelerating marketing asset production.
Tech Stack: Stable Diffusion, DreamBooth, Hugging Face Diffusers, Prompt Engineering, Python, Gradio UI, Image Augmentation
🎨 Realistic Product Visualization Using DreamBooth & Hugging Face
During my internship, I developed a generative AI pipeline to convert raw product samples into realistic, human-worn visuals for marketing and branding purposes. The workflow involved fine-tuning a Stable Diffusion model using DreamBooth with company-provided sample images. Guided prompts were designed to control visual attributes like pose, lighting, and context. This solution enabled the generation of high-fidelity synthetic visuals, eliminating the need for physical photoshoots and accelerating marketing asset production.
Tech Stack: Stable Diffusion, DreamBooth, Hugging Face Diffusers, Prompt Engineering, Python, Gradio UI, Image Augmentation
🛡️ Malicious SQL Query Detection
Developed a security-focused system to detect malicious SQL queries before execution. The pipeline starts with lexical analysis to tokenize SQL inputs and extract meaningful patterns. Features such as keyword frequency, nesting levels, and suspicious patterns were engineered and fed into ML classifiers. Used labeled datasets of benign and malicious queries to train models. Achieved significant improvement in detection accuracy by combining lexical and statistical approaches.
Tech Stack: Python, Scikit-learn, Lexical Analysis, NLP, SQL, Data Preprocessing, Regex
🛡️ Malicious SQL Query Detection
Developed a security-focused system to detect malicious SQL queries before execution. The pipeline starts with lexical analysis to tokenize SQL inputs and extract meaningful patterns. Features such as keyword frequency, nesting levels, and suspicious patterns were engineered and fed into ML classifiers. Used labeled datasets of benign and malicious queries to train models. Achieved significant improvement in detection accuracy by combining lexical and statistical approaches.
Tech Stack: Python, Scikit-learn, Lexical Analysis, NLP, SQL, Data Preprocessing, Regex
🛡️ Malicious SQL Query Detection
Developed a security-focused system to detect malicious SQL queries before execution. The pipeline starts with lexical analysis to tokenize SQL inputs and extract meaningful patterns. Features such as keyword frequency, nesting levels, and suspicious patterns were engineered and fed into ML classifiers. Used labeled datasets of benign and malicious queries to train models. Achieved significant improvement in detection accuracy by combining lexical and statistical approaches.
Tech Stack: Python, Scikit-learn, Lexical Analysis, NLP, SQL, Data Preprocessing, Regex
🧠 Multimodal Brain Tumor Segmentation with Explainable AI
Developed and compared deep learning models (ResAttUNet, DeepLabV3+, U-Net with BesNet) to perform accurate brain tumor segmentation using multimodal MRI slices (FLAIR, T1, T1ce, T2). Integrated Grad-CAM and Integrated Gradients to visualize model focus, improving interpretability and clinical relevance. Achieved a highest Dice Score of 0.8448 with DeepLabV3+ and spatial precision using ResAttUNet.
Tech Stack: Python, PyTorch, ResAttUNet, DeepLabV3+, U-Net, BesNet, Grad-CAM, Integrated Gradients, NumPy, OpenCV, Matplotlib, Medical Image Preprocessing (NIfTI), Dice Score Evaluation
🧠 Multimodal Brain Tumor Segmentation with Explainable AI
Developed and compared deep learning models (ResAttUNet, DeepLabV3+, U-Net with BesNet) to perform accurate brain tumor segmentation using multimodal MRI slices (FLAIR, T1, T1ce, T2). Integrated Grad-CAM and Integrated Gradients to visualize model focus, improving interpretability and clinical relevance. Achieved a highest Dice Score of 0.8448 with DeepLabV3+ and spatial precision using ResAttUNet.
Tech Stack: Python, PyTorch, ResAttUNet, DeepLabV3+, U-Net, BesNet, Grad-CAM, Integrated Gradients, NumPy, OpenCV, Matplotlib, Medical Image Preprocessing (NIfTI), Dice Score Evaluation
🧠 Multimodal Brain Tumor Segmentation with Explainable AI
Developed and compared deep learning models (ResAttUNet, DeepLabV3+, U-Net with BesNet) to perform accurate brain tumor segmentation using multimodal MRI slices (FLAIR, T1, T1ce, T2). Integrated Grad-CAM and Integrated Gradients to visualize model focus, improving interpretability and clinical relevance. Achieved a highest Dice Score of 0.8448 with DeepLabV3+ and spatial precision using ResAttUNet.
Tech Stack: Python, PyTorch, ResAttUNet, DeepLabV3+, U-Net, BesNet, Grad-CAM, Integrated Gradients, NumPy, OpenCV, Matplotlib, Medical Image Preprocessing (NIfTI), Dice Score Evaluation
Skills
Skills
Python
Machine Learning
Deep Learning
Generative AI
Pytorch
MySQL
Power BI
Java
Scikit-learn
Git/Github
Rest API
AWS
NLP
Tensorflow
UI Design
+ More
+ More
+ More
Academic Background and Aspirations
Academic Background and Aspirations
I am a 2025 B.Tech graduate in Computer Science and Engineering with a specialization in Artificial Intelligence. Since the beginning of my academic journey, I’ve been deeply passionate about AI and its potential to drive impactful, intelligent systems. From early coursework in machine learning to building complete end-to-end AI applications, I’ve pursued this field with determination and curiosity.
My first formal experience with AI in industry was at Feynn Labs, where I explored how machine learning could drive product development in the Indian cosmetics market. Working remotely, I analyzed data from over 15 local skincare and beauty brands using unsupervised learning and clustering techniques. The aim was to uncover consumer preferences, market gaps, and emerging trends. I applied k-means and hierarchical clustering on product feature matrices that included pricing, ingredient tags, and popularity metrics. The resulting insights helped identify three untapped market segments. These insights were handed off to the formulation team, who used them to prototype new product lines more aligned with consumer expectations. This project helped me see how data analysis directly supports R&D, brand strategy, and innovation.It was during this internship that I realized how impactful applied AI can be in shaping tangible outcomes beyond screens and code. This experience gave me the confidence to continue pursuing AI not just as a technical skill, but as a driver of value in real-world domains like health, fashion, and consumer goods.
After witnessing how powerful generative models can be, I became interested in the risks and ethical challenges associated with AI. This led me to an externship where I collaborated with a global cohort of students and mentors to study bias, fairness, and accountability in AI systems. We analyzed case studies like facial recognition bias and recommendation engine discrimination. I contributed to a team presentation where we proposed actionable guidelines and fairness metrics. This experience gave me international exposure, taught me the importance of responsible AI, and shaped my belief that ethics and explainability must go hand in hand with innovation.
Summer Internship – Digital and AI Intern
Currently, I’m interning as a Digital and AI Intern where I’ve worked on data analytics, real-time dashboards, and process understanding. One of my initial tasks was to reverse-engineer a thermal incident project, understand the data pipelines behind it, and assist in validating the new improvements. I also worked on custom visualizations to track performance metrics. Building on this, I transitioned into a Hugging Face-based workflow where I designed tools to assist with visual quality checks for industrial marketing teams. These projects gave me exposure to both cloud infrastructure and cross-team collaboration.
Ongoing Research – Brain Tumor Segmentation In parallel, I’m co-authoring two academic journal papers on brain tumor segmentation. These are based on the work I’ve done with deep learning models like DeepLabV3+ and ResAttUNet on the BraTS dataset. My focus is not just on model development, but also on the interpretability side—using techniques like Grad-CAM to ensure clinical trust. These papers aim to contribute toward building AI that is both effective and explainable in critical healthcare domains.
Each of these experiences has helped me grow from an AI learner to an AI practitioner. I’ve learned how to solve real problems with code, how to present work to diverse teams, and most importantly, how to keep learning with purpose and curiosity.