Omkar Ravada

I sit at the intersection of quantum computing and machine learning — building hybrid classical-quantum systems that push beyond what classical models alone can achieve.
My foundation is in classical ML end-to-end pipelines spanning Logistic Regression, Random Forest, XGBoost, Gradient Boosting, SVMs, and K-Means clustering, deployed on AWS and Azure cloud infrastructure. My internship work at Deloitte and Innomatics Research Labs gave me production-grade exposure to scalable AI systems, GenAI tooling, and real-world data pipelines.
I'm now actively applying these foundations to Quantum Machine Learning (QML) exploring Variational Quantum Circuits (VQCs), the Quantum Approximate Optimization Algorithm (QAOA), and quantum-enhanced feature spaces using PennyLane and Qiskit. I'm particularly drawn to hybrid architectures where quantum layers replace or augment classical neural network components, and to near-term NISQ-device applications in optimization and classification.
My technical stack spans: Python · TensorFlow · Scikit-learn · PennyLane · Qiskit · SQL · AWS / Azure · Splunk.