Hari Shrawgi

[email protected] | [email protected] | +91-9584233799 | www.linkedin.com/in/harishrawgi/

Education
Date Degree Institute Performance
2019-2021 M. Tech AI Indian Institute of Science 9.7/10 (Top of the batch)
2014-2018 B. Tech. Computer Science National Institute of Technology Raipur 9.61/10
28/05/2014 AISSCE (CBSE) for Class XII Krishna Public School, Bhilai 89.6%
04/06/2011 AISSE (CBSE) for Class X Krishna Public School, Bhilai 9.0/10.0
Certifications
Year Certifications Organization Performance
2019 Graduate Aptitude Test for Engg. (GATE) CS MHRD, India AIR-6
2016 Machine Learning Stanford University (Coursera) 97.3%
2015 Ethical Hacker IIT Delhi A+ grade
2012 ESOL Examination University of Cambridge Distinction

Professional Experience
• Data Scientist Intern, Microsoft (May 2020 – Jul 2020)
o Interned with the ‘Trustworthy Fundamentals’ team at Bing which focuses on issues around Trust and Fairness
o Developed ML/DL models to detect search queries which can lead to misinformation and hatred
o Built a prototype twitter bot to check if a tweet is spreading political misinformation
• R&D Software Engineer, Broadcom (CA Technologies) (Jul 2018 - Apr 2019)
o Worked as an R&D Engineer for CA Single Sign-on which is a large-scale enterprise security product
o Led design and development of the Cross-Origin Resource Sharing (CORS) feature of CA SSO
o Designed a new Block-chain based ledger system for new hires joining Broadcom
• Research Intern, Australian National University (Jun 2017 - July 2017)
o Integrated Machine Learning with ongoing Biomedical research
o Identified new Biomarkers for diagnosis of CFS/ME neural disease
o Also developed a model to evaluate the performance of various pathological labs across Australia
Recent Projects
• Detecting Suspicious Political Queries on Bing (2020)
o Developed a model to detect suspicious political queries in order to prevent misinformation leakage from Bing
o Designed and implemented a custom BERT model based on manually engineered features along with query text
o Improved the Precision/Recall of existing query detection pipeline from (87/06) to (90/58)
• Sample complexity reduction for Deep Reinforcement Learning algorithms (2020)
o Developed a new technique to reduce training sample requirements for Hierarchical RL algorithms
o The technique recycles the data collected at a lower temporal scale for training higher temporal layers
o Reduced the training data required by HDQN for achieving maximum averaged reward by 50%
• CNN based guide prediction for CRISPR/Cas9 gene editing tool (2018)
o Designed a CNN model trained over 400,000 data points to predict best SgRNA guides to be used by CRISPR
o Eliminated the need for feature engineering, a major pain point of automating guide selection for CRISPR
o The model outperformed all competing State-of-the-art models at the time
• Bio-marker identification for Chronic Fatigue Syndrome (CFS) (2017)
o Used Neural Networks coupled with ROC curve analysis to discover biomarkers for clinical diagnosis of CFS
o Substantiated the results with a systematic review on 60 NCBI research works and articles
o The new biomarkers can lead to detection of CFS through pathological tests which was not feasible before
• UNICEF Pregnancy Assistant App (2017)
o Winning android app of the UNICEF recognition award for a solution to Maternal & Newborn Health theme
o Implemented text-to-speech for visually impaired or illiterate women and also incorporated the Prime Minister’s
scheme for free antenatal care to support financially weak patients
o Used Agglomerative clustering to detect regions which require focused development in antenatal care
Recent Publications (2 among a total of 5 publications)
• Shrawgi, H. and Sisodia, D.S., 2019. Convolution neural network model for predicting single guide RNA efficiency
in CRISPR/Cas9 system. Chemometrics and Intelligent Laboratory Systems, 189. (Impact factor: 2.3)
• Sharaff, A., Shrawgi, H. and Verma, A. 2018. Generic Document Classification Using Clustering, Centrality, and
Voting. In: Mandal J.K. et al (eds.). Proceedings of the International Conference on Computing and Communication
Systems. Lecture Notes in Networks and Systems, Vol. 24. Springer.
Awards & Community Service
• UNICEF special award, Codeutsava: In recognition of developing the best solution in Maternal Health theme (2017)
• Founded and led an NGO - Inspire Foundation and taught 950 underprivileged students throughout Raipur district (2016)
• Worked as a volunteer in Unnat Bharat Abhiyan to teach rural students in a remotely located govt. school (2017)