Varun Khare is a founder-CEO and applied AI engineer with a decade of experience building on-device, privacy-first intelligence—currently leading NimbleEdge to run quantized LLMs and speech pipelines entirely offline. He bridges top-tier research (UC Berkeley, Max Planck) and productisation, turning innovations like tokenizer batching and Sparse Transformers into an open-source stack (github.com/NimbleEdge/deliteAI) for real-time, session-aware mobile AI. Previously he led federated learning efforts at OpenMined, shipping peer-to-peer, secure aggregation and SMPC tooling for on-device ML. Varun’s background spans deep learning, distributed systems and computer vision, including peta-byte scale connectomics and monocular 3D reconstruction, which informs his focus on decentralized inference, kernels and developer platforms. Based in San Francisco, he combines academic rigor with hands-on engineering to make low-latency, private AI practical across smartphones, wearables and sensors.
10 years of coding experience
3 years of employment as a software developer
Indian Institute of Technology Kanpur
higher education, higher education at Delhi Public School Bhopal
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.