Vanshaj Awasthi — Full Stack Developer | AI & Data Engineering
I build AI-powered applications, backend systems, and data-driven products — combining full-stack engineering with hands-on AI/ML experience. My work spans PostgreSQL and Supabase-backed systems, OpenAI and RAG integrations, and production-grade full-stack delivery, backed by a research portfolio of 17+ IEEE and Springer publications in medical AI and deep learning.
Full Stack Software Developer building AI-powered applications and data-driven systems — with a research background of 17+ IEEE-published papers in medical AI and deep learning, based in Pune, Maharashtra. Full Stack Software Developer at Evonix Technologies, building full-stack applications, backend systems, and AI integrations — with a research portfolio of 17+ publications spanning medical AI diagnostics, deep learning, and neural engineering.
About
To engineer intelligent systems that bridge the gap between biological complexity and computational precision.
Experience
- Full Stack Software Developer — Evonix Technologies Pvt. Ltd. (Jan 2026 - Present). Promoted from intern to full-time, taking increasing ownership of production applications and client-facing software projects. Build full-stack applications across frontend, backend, APIs, authentication, database architecture, and deployment. Work extensively with PostgreSQL and Supabase, including Supabase Edge Functions, and build backend workflows with Python. Integrate AI capabilities using OpenAI APIs, NLP, RAG, embeddings, vector databases, and AI agents, and use Redis where appropriate for application workflows. Implement authentication, OAuth, RBAC, payments, and secure API integrations, and deploy across AWS and Railway.
- AI/ML Lead — Google Developers Group (Sep 2024 - Jul 2025). Led a 170-member AI/ML-focused community, delivering around 20 AI/ML training sessions and organizing 4 technical competitions. Developed industry-aligned curricula, mentored members on AI/ML topics, and coordinated technical and community initiatives.
- Software Developer (Intern) — Evonix Technologies Pvt. Ltd. (Jul 2024 - Jan 2026). Built and shipped production features across the full stack, working with backend and API development, PostgreSQL and Supabase, and AI/chatbot conversational functionality. Contributed to debugging, integration, and application development, laying the groundwork that led to a full-time offer.
Education
- Bachelor of Technology - Computer Science — Amity University Mumbai, July 2022 - April 2026. Graduated | 9.36 CGPA | Minor in Business Management
- Higher Secondary Education (CBSE) — Ambika Prasad Memorial Public School, 2019 - 2021. 86% (Physics, Chemistry, Mathematics)
Research Publications
- Deciphering Molecular Subtypes in Uterine Corpus Endometrial Carcinoma — IEEE. Leveraging machine learning to uncover distinct molecular signatures and histological markers for personalized therapeutic strategies.
- Interpretable Deep Learning for Knee Osteoporosis Screening — IEEE. Employs ResNet-18 with feature attention for accurate osteoporosis detection from knee X-rays with clinical interpretability.
- A Disaster Prediction Ensemble Classifier Using Artificial Intelligence — IEEE (MoSICom 2024). Introduces the Ensemble B-Classifier Network (DE BCN) for improved disaster forecasting, leveraging multi-model integration and Mustard Twin Swarm optimization.
- GenAI-Enhanced Brain-Computer Interface for Assistive Communication — IEEE (ICEIL 2024). Proposes a GAN-augmented BCI framework that breaks communication barriers for individuals with physical disabilities, achieving a 20% improvement in character recognition speed.
- Automated Alzheimer's Disease Detection via 3D ResNet and Hippocampal Atrophy Mapping — IEEE. A 3D-ResNet backbone with multi-scale feature fusion achieves 97.31% classification accuracy in early-stage Alzheimer's detection from high-resolution MRI volumes.
- CLAHE-Augmented MRI Dementia Classification via Soft-Voting Ensemble with Gradient-Based Analysis — Springer Nature. Soft-voting ensemble (ResNet-50, DenseNet-121, ConvNeXt, Swin Transformer, ViT) with CLAHE preprocessing achieves AUC-ROC 0.99/0.97 across 87,000+ MRI scans for dementia severity classification.
- AI-Optimized Wireless Power Transfer Systems for Implantable Medical Devices: Enhancing Energy Efficiency in Parkinson's Neurostimulation — Springer Nature. AI-driven WPT framework achieving >85% energy transfer efficiency, 250 mW stable delivery at 10 mm, ≤1.5°C temperature rise, and 1,200+ hours in-vitro stability for Parkinson's neurostimulators.
- Exploring the Therapeutic Potential of Electromagnetic Field Exposure from WPT Systems in Neural Regeneration Post-Spinal Cord Injury — Springer (2nd Symposium on Smart, Sustainable, and Secure IoT). Controlled EMF exposure from WPT demonstrates 40% improvement in movement performance vs. untreated controls, with enhanced axonal growth, myelin repair, and reduced neuroinflammation.
- Attention-Augmented MobileNetV2 for MRI-Based Brain Tumor Classification: Cosine Annealing and Advanced Metrics — Springer LNNS (ICACIT 2024). Attention mechanisms integrated into MobileNetV2 with cosine annealing and stratified k-fold validation for glioma, meningioma, and pituitary tumor classification. ROC-AUC: 0.9703.
- Synergizing GAN-Driven Synthetic Data Pipelines with Deep Neural Networks for Enhanced Breast Cancer Diagnosis — Springer LNNS (ICACIT 2024). GAN-generated synthetic histopathology images augment CNN training to achieve 99.17% accuracy, 100% recall, MCC 0.9801, and ROC-AUC 0.9998 for benign vs. malignant classification.
- Priority-Driven MAC Protocol Design for IoT-Enabled Wireless Body Area Networks — Springer LNEE (FLAME 2024). Priority-aware MAC protocol for WBANs reduces signal collisions, cuts energy consumption, and improves reliability for real-time IoT health monitoring systems.
- Reinforcement Learning and Spatio-Temporal GNNs for Alzheimer's Disease Progression Prediction with VAE-Based Data Imputation — IEEE ICETET-SIP 25. Spatio-temporal GNNs + reinforcement learning + VAE-based imputation for Alzheimer's progression modeling across 2,149 ADNI MRI scans. 98.2% accuracy. Best Paper Award at GHRCE Nagpur.
- Hybrid RBC Morphology Analysis and Diagnostic Framework for β-Thalassemia Using SEBlock-CBAM Enhanced MobileNetV2 and TabNet — IEEE ICCSAI 2025. Hybrid diagnostic pipeline for β-thalassemia: attention-augmented MobileNetV2 for RBC morphology + TabNet for tabular blood data, with Optuna and SMOTE-ENN. 90.8% RBC accuracy, 90% precision.
- Hybrid 3D CNN and ResNet Deep Transfer Learning for High-Resolution Hippocampal Atrophy Mapping and Automated Alzheimer's MRI Diagnosis — ETASR – Engineering, Technology & Applied Science Research (Scopus Q2). 3D U-Net hippocampal segmentation fused with multi-scale ResNet achieves 97.31% accuracy and 92.84% DSC. Validated on ADNI + OASIS datasets with Grad-CAM and SHAP interpretability.
- Neuro-Oncology Reimagined: Tailored Prognosis for Brain Tumors Using Adaptive Machine Learning — IEEE. Adaptive ML with Random Forest, SMOTE, and algorithmic fairness achieves 98.36% brain tumor prognosis accuracy, integrating multi-omics data with bias mitigation across diverse populations.
- Survey on Asclepius: A User-Centric Chatbot Bridging the Gap in Healthcare Integrated with VPN Technology — IEEE AECE 2024. Asclepius: an AI healthcare chatbot achieving 89% diagnostic accuracy via supervised decision trees, VPN-secured communications, and facial recognition for privacy-first patient interactions.
- Analysis and Impact of Electromagnetic Field Leakage in Wireless Power Transfer on the Central Nervous System: A Neural Network Approach — IEEE Sustainable Energy & Future Electric Transportation 2024. Neural network modeling of EMF absorption from WPT systems on CNS tissue, informing bioelectromagnetics safety guidelines. Best Paper Award at IEEE Sustainable Energy 2024.
All 17 publications
Awards
- Best Paper Award — Track 6 — IEEE ICETET-SIP 25, G.H. Raisoni College of Engineering, Nagpur (2025) for “Reinforcement Learning and Spatio-Temporal GNNs for Alzheimer's Disease Progression Prediction with VAE-Based Data Imputation”
- Best Paper Award — IEEE 4th International Conference on Sustainable Energy and Future Electric Transportation 2024 (2024) for “Analysis and Impact of Electromagnetic Field Leakage in Wireless Power Transfer on the Central Nervous System: A Neural Network Approach”
Skills
- Software Engineering: React, Next.js, Node.js, TypeScript, Python, JavaScript, Vite, Framer Motion, Git, C++, Java, C, Bash/Shell, Linux, VS Code, Figma, Project Leadership
- Backend & Data: PostgreSQL, Supabase, Supabase Edge Functions, Redis, REST APIs, SQL, MongoDB, FastAPI, Flask, GraphQL
- AI Engineering: OpenAI API, NLP, RAG, Embeddings, Vector Databases, AI Agents, Generative AI, Machine Learning, Deep Learning, Computer Vision, PyTorch, TensorFlow, LangChain, Hugging Face, OpenCV, Keras, Scikit-learn, Optuna, Pandas, NumPy, Matplotlib, Seaborn, Jupyter
- Cloud & Infrastructure: AWS, Railway, Azure, GCP, Docker, Nginx, CI/CD
- Application Engineering: Authentication, OAuth, RBAC, Payments, Realtime, File Storage, Notifications, Mobile
Certifications
- Machine Learning Specialization — DeepLearning.AI / Stanford University (2025)
- Advanced Learning Algorithms — DeepLearning.AI / Stanford University (2025)
- Supervised Machine Learning: Regression & Classification — DeepLearning.AI / Stanford University (2025)
- Unsupervised Learning, Recommenders & Reinforcement Learning — DeepLearning.AI / Stanford University (2025)
- AWS Cloud Technical Essentials — Amazon Web Services (AWS) (2024)
- Generative AI: Introduction and Applications — IBM / Coursera (2024)
- Generative AI: Foundation Models and Platforms — IBM / Coursera (2025)
- Generative AI: Prompt Engineering Basics — IBM / Coursera (2024)
- Preparing Data for Analysis with Microsoft Excel — Microsoft / Coursera (2025)
- Python for Data Science, AI & Development — IBM / Coursera (2024)
- Deep Learning with PyTorch: Build a Neural Network — IBM / Coursera (2024)
- Introduction to Artificial Intelligence (AI) — IBM / Coursera (2024)
- Neural Networks and Deep Learning — DeepLearning.AI (2024)
- Getting Started with Git and GitHub — IBM / Coursera (2023)
- Python 101 for Data Science — IBM / Cognitive Class (2023)
- Building Data Analyst AI Agent — Analytics Vidhya (2024)
- Introduction to Data Engineering — DeepLearning.AI & AWS / Coursera (2024)
- Migrating to the AWS Cloud — AWS / Coursera (2024)
Writing
Connect