Close

Hari Shrawgi

AI Researcher

Download Resume

About Me

Hari Shrawgi is an MTech AI student at the Indian Institute of Science where he is working to improve the theoretical foundations of deep learning. He got interested in ML during his under-graduation, doing extensive applied research which led to five research publications. Working on sensitive applied domains such as biomedicine and gene-editing, he realized the need for trustworthy and explainable AI. This need underpins his research goal - to develop theory that can lead to more trustworthy AI models. In his free time, he loves saving virtual worlds in video games.

Education

Indian Institute of Science

August 2019 - May 2021

Master of Technology in Artificial Intelligence

National Institute of Technology Raipur

August 2014 - May 2018

Bachelor of Technology in Computer Science

Experience

Microsoft

Data Scientist Intern

Interned with the ‘Trustworthy Fundamentals’ team at Bing which focuses on issues around Trust and Fairness. Majority of my time as an intern was devoted to building models to detect search queries that can spread political misinformation and hatred. I also developed a twitter bot using these models to detect tweets which may lead to misinformation.

    Developed a model to detect suspicious political queries in order to prevent misinformation leakage from Bing
    Designed and implemented a custom BERT model based on manually engineered features along with query text
    Improved the Precision/Recall of existing query detection pipeline from (87/06) to (90/58)

Broadcom (CA Technologies)

R&D Engineer

Worked as an R&D Engineer for the product CA Single Sign-on under the security division. It is a product that serves most of the Fortune 500 companies and is deployed on the biggest scales of enterprise software in the world. Following are the highlights of my contribution to the product and the company:

    Designed and implemented a feature to support Cross Origin Resource Sharing across SSO. It allows customers to use different domains without the browser restricting the request-response flow.
    Designed a prototype to implement a ledger system to track new hire onboarding. The ledger system was based on blockchain technologies.

Australian National University

Research Intern

Worked under the guidance of Prof. Brett Lidbury in the interdiscilinary field of Bioinformatics:

    Applied machine learning and data mining to biomedical research data
    Identified new bio-markers for diagnosis of CFS/ME neural disease
    Developed a model to evaluate the performance of various pathological labs across Australia

Recent Projects

Sample complexity reduction for Deep Reinforcement Learning algorithms

Developed a new technique to reduce training sample requirements for Hierarchical RL algorithms. The technique recycles the data collected at a lower temporal scale for training higher temporal layers. The technique is very easy to plug into most existing and widely used HRL algorithms. The techinque was observed to reduce the training data requirements for HDQN by 50% in a simple MDP setup.

CNN based guide prediction for CRISPR/Cas9 system

The CRISPR/Cas9 system for gene editing relies heavily on the selection of a good RNA guide. The manual selection process is both difficult and expensive. As part of my B. Tech major project, I developed a CNN model to automate this process. Below are short pointers related to the project: The model was trained on over 400,000 data points from approx. 400 human cell lines. The model outperformed all conventional machine learning models which are dependent on feature enineering.

View Publication related to this project.

Bio-marker identification for Chronic Fatigue Syndrome

Used Neural Networks coupled with ROC curve analysis to discover biomarkers for clinical diagnosis of CFS. Substantiated the results with a systematic review on 60 NCBI research works and articles. The new biomarkers can lead to detection of CFS through pathological tests which was not feasible before.

Skills

Achievements and Community Service

  • Secured All India Rank 6 among 100,000 candidates in GATE 2019 exam.
  • Winner of UNICEF special recognition award for designing the best android app for Maternal and Antenatal care.
  • Worked with the District Education Officer of Raipur to teach 950 underprivileged students throughout the district.
  • Taught biology and mathematics to rural students in a remotely located govt. school as a volunteer to the Unnat Bharat Abhiyan programme.