Section 1: Professional Experience & Work Projects
​
Datastrato.ai | Software & Data Engineering Intern
Jun 2024 – Aug 2024 | San Jose, California
Project: Apache Gravitino Metadata Discovery Integration
​​​​
-
Integrated Apache Gravitino with 5+ diverse ML datasets,
-
Streamlining metadata discovery and reducing onboarding time by 30%.​
-
Optimized CI/CD pipelines using Dockerized test environments
-
Resulting in a 15% boost in deployment reliability.​
-
Authored technical documentation for high-scale data infrastructure.
Vodafone Qatar | Software Engineer (Backend Systems)
Aug 2021 – Mar 2022 | Pune, India
​​​​
-
Architected end-to-end CRM workflows using Bonitasoft BPMN,
-
Automated manual verification processes for thousands of subscribers and Sim Card Users.​
-
Developed robust Java-based backend services and RESTful APIs.
-
Synchronized real-time customer data across legacy systems.​
-
Collaborated with cross-functional teams to deploy updates in an Agile/Scrum environment.
-
Maintained 99.9% system uptime.
Project: Enterprise Product CRM Workflow Automation
Section 2: Research & Academic Projects
​
Purdue University | Research Assistant (AI for Social Good)
Feb 2023 – May 2024 | Fort Wayne, Indiana
Project: Fairness-Aware Deep Learning in Healthcare
​​
-
Engineered AIFairness360 deep learning architectures that improved model recall.
-
Manual Data Cleaning, Processing and Hyper Parameter Tuning for underrepresented demographic.
-
Built reproducible MLOps pipelines that slashed model experimentation and training time by 40%.
-
Conducted bias evaluations on large-scale biomedical datasets to inform ongoing clinical research studies.
-
Collaborated with Professor Alessandro Selvittela, and Project Managers in Lab of Data Science.
PixelPerfectAI | Image Enhancement SaaS Web App
​
Tech Stack: Python, PyTorch, Docker, React, Flask, Redis
​
-
Developed a full-stack SaaS application using ESRGAN and GFPGAN for high-fidelity image restoration.
-
Implemented a distributedarchitecture with containerized workers to handle async image processing tasks.
-
Achieved a 99.5% job success rate with low latency, processing 50+ high-resolution images daily.
-
Used NextJS, Supabase, PostgreSQL, NeonDB and Async Job Processing along with RestAPIs.
​
EduLoyalty | Gamified Reward Platform
Tech Stack: TypeScript, React, SQL, Flask
​​
-
Engineered AIFairness360 deep learning architectures that improved model recall.
-
Manual Data Cleaning, Processing and Hyper Parameter Tuning for underrepresented demographic.
-
Built reproducible MLOps pipelines that slashed model experimentation and training time by 40%.
-
Conducted bias evaluations on large-scale biomedical datasets to inform ongoing clinical research studies.
-
Collaborated with Professor Alessandro Selvittela, and Project Managers in Lab of Data Science.
Emotion-Cause Extraction | NLP Research (SemEval 2024)
Tech Stack: RoBERTa, Hugging Face, Python
-
Detected emotion-cause in sentences using transformer to identify emotional triggers in FRIENDS dataset.
-
Optimized tokenization and preprocessing workflows, reducing total model training time by 28%.
-
Achieved 74% accuracy, placing the model in a competitive rank against global SemEval benchmarks.
Section 3: Publications (The "Citations" Impact)
​
Multimodal AI & Sensor Fusion for Industrial Safety
Symbiosis Centre of Applied Artificial Intelligence | Pune, India
Tech Stack : CNN, LSTM, Numpy, Pandas, Sensor Fusion
-
Architected a CNN-LSTM Hybrid Model for Gas Leakage Detection that fused thermal imagery and
-
chemical sensor data, achieving 96% accuracy in real-time gas leak detection and identification.
-
Curated & Published "MultimodalGasData" - a custom dataset (published in MDPI Data) involving
-
manual thermal data collection and 3x data augmentation.
-
Outperformed single-modality industry baselines by 12-18%, providing a fail-safe mechanism.
-
Co-authored 5 peer-reviewed papers with 210+ total citations, in mulitmodal sensor fusion.
Applied System Innovation (127 Citations)
​
-
Developed a novel multimodal fusion framework using CNNs for thermal spatial features and
-
LSTMs for temporal sensor sequences, significantly reducing false alarm rates in gas detection.
Soft Computing – Industry 5.0 Tasks (42 Citations)
​
-
Evaluated the robustness of co-learning algorithms against sensor noise and failure, ensuring 99.9% reliability for automated industrial monitoring systems.
MDPI Data – MultimodalGasData (37 Citations)
​​
-
Engineered a standardized data collection pipeline for chemical sensors and thermal cameras, creating a publicly available benchmark dataset for the AI research community.