Pranav Taneja is a Software Engineer III with nine years of experience, currently enabling state-of-the-art AI on Edge TPU devices at Google to reduce latency, improve privacy, and broaden access to AI. He combines hands-on ML systems work—pretraining, fine-tuning, RLHF/DPO alignment and data augmentation for billion-token corpora—with low-level performance engineering on CUDA/HIP and compiler optimizations. At Krutrim he built multi-agent code-generation systems, prompt-suggestion UX features, and LLM-powered demo agents, and earlier contributed LLVM improvements for AMD GPUs. This blend of application-level multi-agent design and compiler/GPU optimization gives him a rare end-to-end view of LLM training and inference bottlenecks. Based in Punjab, India, he pairs an MS in Economics and a BE in Computer Science from BITS Pilani with a passion for empowering users through practical AI deployment. An understated strength is his track record of turning research-scale models and massive synthetic datasets into usable, optimized systems for real-world edge devices.
9 years of coding experience
2 years of employment as a software developer
BITS Pilani, Birla Institute of Technology and Science
Contributions:1 push, 1 branch, 1 issue in 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.