● Designed and developed a production-grade radar alignment solution in C++ from concept to production, powering 500k+ BMW vehicles with enhanced object-tracking performance.

● Enabled new algorithm features through radar data analysis using Python (NumPy, Pandas) and Matlab, driving a 20% precision boost in radar perception systems.

● Devised a C++ debug logging utility with bit-level optimizations using bit masks and macros, enabling 30% faster issue reproduction and enhancing developer efficiency in radar feature development.

● Pioneered ML-based data filtering techniques, using adaptive learning to eliminate noisy detections and optimize processing, saving $2.5M annually for BMW.

● Engineered a data visualization platform in Python and React streamlining team workflows and saving 300+ hours annually.

● Architected and implemented static alignment feature through close collaboration with radar and integration teams, achieving a 60% improvement in startup alignment accuracy.

● Built scalable data tools using AWS scripting and automation, resulting in a 30% reduction in compute resource usage.

● Established GTest and Jenkins-based validation infrastructure, achieving 100% test coverage and increased algorithm stability.

● Designed and developed a hybrid car tracking feature in C++ leveraging ML and radar fusion, improving object tracking accuracy and precision for real-time autonomous driving scenarios.

● Engineered fusion and filtering enhancements for the tracking algorithm, achieving an 18% gain in accuracy and system reliability.

● Applied memory-efficient design patterns and refactored radar codebase, minimizing runtime space usage by 20%.

● Developed a performance evaluation tool in Python and Matlab, automating analysis and reducing KPI generation time by 40%.

● Assisted in teaching and grading for a graduate-level course on Data Structures and Algorithms, Data Science, and Machine Learning, serving as a valuable resource for students with varying levels of programming experience.

● Demonstrated understanding of key concepts such as time complexity, big-O notation, and various data structures (e.g. arrays, linked lists, stacks, queues, trees, graphs, etc.)

● Supported in designing and implementing projects related to data cleaning, data exploration, and machine learning modeling using Python, R, and SQL.

● Demonstrated expertise in machine learning techniques such as classification, regression, clustering, and deep learning.

● Organized and led quarterly events for 300+ participants, ensuring seamless execution and engagement.

● Facilitated 10+ seminars and workshops, enhancing campus awareness of Dell’s technology and opportunities.

● Routinely addressed student queries, acting as a key liaison between students and Dell representatives.