I am an AI Engineer and Data Scientist driven by a passion for multimodal intelligence, deep learning, and statistical modeling. My work focuses on transforming complex data into meaningful insights and practical solutions across diverse domains, while my research delves into Generative AI, Trustworthy AI, and Human-AI collaboration, aiming to advance methods that connect innovation with real-world impact.
Designing Intelligent, Scalable Systems from Data to Deployment
Generative AI, Large Language Models (LLMs) & Foundation Models
Retrieval-Augmented Generation (RAG) systems at scale
AI Agents & tool-based autonomous workflows
Computational neuroscience & multimodal learning
Time-series forecasting, probabilistic & Bayesian modeling
Real-time analytics, monitoring & AI-driven insights
Cloud-native SaaS & AI platforms
FastAPI & Next.js powered APIs and dashboards
AI system integration with cloud services
SQL, NoSQL & Vector databases
Secure, scalable deployments with containers
Enterprise BI dashboards & semantic modeling
Data engineering pipelines & lakehouse architectures
Data governance, quality, and analytics enablement
Real-time & batch data processing
Thesis: “Child Behavior Classification using Machine Learning” – predictive modeling on health time-series data.
course work in applied mathematics & statistics and computer science.
Real-time TTS & ASR for broadcast media; transformer pipelines; AI-driven multimedia analytics dashboards.
Developing enterprise BI solutions using Power BI and Microsoft Fabric, focusing on data modeling, governance, and scalable analytics dashboards.
Fine-tuned Llama-2-7B (4-bit QLoRA) on 4 M social posts (hate-speech F1=0.89); built live social-media streams & policy dashboards.
U-Net OCT segmentation; hyperbolic & graph neural nets for cardiovascular diagnostics.
Computer-vision safety stack for AVs: driver-behavior monitoring & object detection with policy-driven urban mobility.
Hierarchical Bayesian models for survey data; semi-supervised EM imputation; behavioral research frameworks.
Enterprise RAG system using Google Cloud Vertex AI, ADK, and Gemini 2.5 Flash with auto-generated backend, Dev UI, and scalable document retrieval.
Lightweight in-app AI chatbot built with Next.js and Gemini, enabling document ingestion and real-time contextual assistance via vector search.
Multimodal SaaS (text, image, audio) via GPT-4-V + Stable Diffusion; 150k API calls/month; LoRA fine-tuning with 8× speed-up.
Real-time GPT-based news summarization and sentiment extraction for MOIB policy dashboards.
U-Net and 3D CNN-based semantic segmentation of tumor regions in volumetric medical scans to improve diagnostic accuracy.
Whisper-based ASR combined with lip-reading for robust speech recognition in noisy environments, with CUDA-accelerated multi-GPU batching.
Machine learning framework for classifying child behavior patterns from longitudinal time-series health data. MSc thesis project.
AI Engineer and researcher open to collaborations, research opportunities, and impactful industry roles. Feel free to reach out for discussions on Generative AI, RAG systems, AI agents, or data platforms.
Data Scientist||Researcher