Parikshit Saikia is a Senior Data Scientist based in Chandigarh with 7 years of experience and a 3-year focus on NLP for the patent domain, transforming dense technical documents into actionable IP insights. At GreyB he built memory- and compute-efficient LLMs and classifiers—fine-tuning Llama-3.1-8B for full-text patent summarization and cutting inference time by 88%, and designing a 31M-parameter patent classifier that improved memory usage by 92%. He has end-to-end product experience across semantic search (PQAI), re-ranking, indexing and real-time span highlighting, plus hands-on skill with DeBERTa-V3 for problem-statement extraction. Comfortable shipping lightweight models for production and edge scenarios, he also brings a background in CV and mobile deployment from AR/VR and OCR projects. Known for squeezing high performance out of constrained models, he pairs practical engineering with domain expertise in intellectual property analytics.
7 years of coding experience
Bachelor of Technology, Computer Science, 8.23 / 10, Bachelor of Technology, Computer Science, 8.23 / 10 at Tezpur University
Contributions:2 PRs, 15 pushes, 3 branches in 10 months
pqaidatabasedocument-database
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.