💳 Loan Eligibility Assistant
Open ↗
Certified Data Scientist • Generative AI Specialist • AI/ML Engineer • 4× Inventor • AI Researcher
I am a Certified Data Scientist and AI Engineer with 7+ of experience designing and deploying enterprise-scale AI systems that merge innovation, governance, and measurable business value. My work bridges research and real-world application - from building generative and predictive intelligence solutions for insurance, banking, and healthcare to developing human-controlled, multi-agent frameworks that ensure safety, transparency, and compliance in autonomous systems. As the inventor of multiple patent-pending AI architectures, including SentraNova and the Agentic Compliance Framework, I focus on creating responsible technologies that empower organizations to innovate confidently while maintaining ethical and regulatory integrity. Passionate about transforming research into impact, I combine technical depth with business acumen to drive the next generation of trustworthy AI solutions.
Invented a control architecture designed to ensure safe, explainable, and override-ready behavior in autonomous AI systems through multi-agent reasoning, interruptibility, and governance memory. (Provisional)
Developed an autonomous, agent-driven compliance platform for enterprise policy violation detection across emails, logs, and support tickets. Uses semantic vector search (FAISS), local language models, and self-learning agents to identify violations and adapt to evolving policy landscapes in real time - without reliance on cloud APIs. Designed for scalability, privacy, and continuous improvement. (Provisional)
Agentic Data Preprocessing and Cleaning System (ADPS) is an autonomous AI framework that detects, diagnoses, and corrects data quality issues across unseen datasets. It uses multiple intelligent agents coordinated by an orchestrator to handle missing values, outliers, imbalance, skewness, and inconsistencies through a detect-decide-apply-evaluate pipeline. (Provisional)
The invention introduces a self-adaptive statistical governor that continuously observes system metrics (CPU, memory, I/O etc.) and autonomously regulates performance modes to maintain dynamic equilibrium. (Provisional)
SentraNova is a governance-first framework for building human-controlled, multi-agent AI systems that remain auditable, policy-aligned, and interruptible. It introduces an orchestration layer where autonomous agents collaborate under real-time human oversight, ensuring transparent and compliant decision-making across enterprise AI environments.
The Self-Governing Memory System is an adaptive AI framework designed to autonomously monitor, regulate, and optimize computational resources in real time. It models system memory as a dynamic ecosystem—balancing performance, stability, and efficiency through continuous feedback and self-learning control.
These research initiatives form the foundation of my ongoing work toward safe, transparent, and self-regulating AI systems that align innovation with human control and accountability.
Focused on Generative AI, scalable MLOps, and cloud-native deployments.
LLMs, RAG, LangChain, Prompt Engineering, OpenAI API, Hugging Face, Vector databases
XGBoost, Random Forest, Time-Series (ARIMA, Prophet), Decision Trees, PCA, NLP
TensorFlow, Keras, CNN/RNN/LSTM, LayoutLMv3, TrOCR
Azure ML, AWS SageMaker, FastAPI, Docker, CI/CD (GitHub Actions, Azure DevOps)
Data Factory, Data Lake, SQL, Purview, PySpark
Power BI, Tableau, Plotly, Dash, Streamlit
Azure ML, experimentation, model training, deployment, and monitoring.
Azure OpenAI, Cognitive Services, orchestration, and responsible AI.
Core Azure data concepts, relational & nonrelational stores, analytics workloads, and services like Azure SQL, Cosmos DB, Synapse, and Power BI.
ML and deep learning foundations, TensorFlow/Keras modeling, MLOps basics, and deploying AI solutions with scikit-learn pipelines.
Python and SQL for data analysis, data wrangling and visualization, introductory machine learning, and an industry-style capstone project.
LLM fundamentals and architectures, prompt engineering, RAG with vector databases, fine-tuning/PEFT, safety and evaluation guardrails, and deploying GenAI apps on cloud using frameworks like LangChain and OpenAI APIs.