Summary
Anudeepsekhar Bolimera is a machine learning and computer vision specialist with 8 years of experience building and deploying real-time AI systems across academia and industry. As a Research Assistant at Carnegie Mellon University, he leads scene understanding efforts, extending semantic segmentation and adapting DETR for scene graph generation while achieving a 0.94 mIoU and 30ms GPU inference with TensorRT. He has engineered production ML APIs and on-device pipelines for large-scale product recognition and mobile biometric onboarding, optimizing models with quantization, pruning, CoreML and ONNXRuntime. His prior work spans medical imaging and ML-Ops—creating compact, high-accuracy segmentation models and a toolkit for efficient Triton deployments that accelerated clinical and production pipelines. Comfortable moving research into constrained hardware (Nvidia Jetson, mobile) and orchestration stacks, he blends deep academic rigor with pragmatic engineering. Based in Pittsburgh, he pairs CMU graduate training with entrepreneurial experience as a co-founder/CTO, making him adept at translating novel research into deployable products.
8 years of coding experience
5 years of employment as a software developer
Bachelor of Engineering (BE) Honors, Electrical, Electronics and Communications Engineering, Bachelor of Engineering (BE) Honors, Electrical, Electronics and Communications Engineering at Birla Institute Of Technology and Science, Pilani Dubai
Master of Science - MS, Electrical and Computer Engineering, Master of Science - MS, Electrical and Computer Engineering at Carnegie Mellon University
English, Hindi, Telugu