• 🌱 Focused on DSA, competitive programming (C++), and structured problem solving
• 🧠 Working on systems that learn from data and analyzing how they behave internally
• ⚡ Exploring performance-aware computing and parallel execution using GPU's and TPU's
• 🤝 Open to collaboration on AI/ML and research-oriented projects

• Studying how learning systems form internal representations from raw data and how different approaches prioritize information

• Building predictive models using combined decision strategies to improve robustness and consistency

• Exploring how model capacity, data complexity, and optimization interact to influence learning behavior

• Solving algorithmic problems with focus on efficiency, edge cases, and complexity analysis (competitive programming in C++)

• Investigating performance aspects of computation, including parallel execution and acceleration

• Mathematical structure behind learning systems
• Behavior of algorithms under constraints (time, memory, scaling)
• Representation learning and information flow inside models
• Trade-offs between accuracy, efficiency, and generalization
• Compute efficiency and parallelism

Moving toward research and engineering at the intersection of:

• intelligent systems
• mathematical reasoning
• algorithmic efficiency
• high-performance computation

Goal is to build systems that are not only effective,
but predictable, scalable, and deeply understood.