Jan 2022 – Jan 2024 · 2 yrs · India · Remote

• Web Entity Extraction and Validation at large scale using Deep Learning and LLMs
• Designed and developed H1’s Entity Validator service based on FastAPI, Flask and
• Transformers framework for efficient data validation and successfully deployed in Web Extraction Pipeline on AWS to improve
• data validation efficiency at large scale, resulting in reduction of turn-around-time of 95%.
• Designed and developed the PySpark Web Extraction pipeline for entity extraction having multiple services which replaced the legacy extraction framework leading to increase in throughput of 600%.
• Engineered algorithms for reverse mapping, voting to identify common XPaths for increased efficiency in extraction by 30%.
• Development of Cleanup module which resulted in increased quality of production data and reduced data issues by 40%.
• Worked on Prompt engineering and fine tuning for OpenAI GPT-3.5-turbo based Entity Extraction increasing recall by 16% and precision by 11%.
• Skills: RDBMS · MySQL · Back-End Web Development · Continuous Integration and Continuous Delivery (CI/CD) · PySpark · SQL · Data Structures · BERT · Apache Spark · Machine Learning Algorithms · Data Engineering · Mathematics · Pandas · NumPy · Data Science · Computer Science · Natural Language Processing (NLP)

Sep 2021 – Aug 2022 · 11 mos

Aug 2019 – Dec 2021 · 2 yrs 4 mos

• Optimized processor resource consumption of Samsung’s Bluetooth algorithm used in flagship models: Scalable Speech Codec
• (SSC) leading to 15% MIPS (Millions of instructions per second) reduction.
• Upgraded Samsung’s Diamond-Voice Module from Q15 to Q24, Q31 format and optimized it, leading to 5% MIPS reduction.
• Optimized SSC Library Audio Codec memory usage for Hifi3 Low Memory chip leading to 40% memory usage reduction.
• Optimized processor resource consumption of SSC Encoder and Decoder Legacy code resulting in 9.1% reduction in MIPS.

May 2019 – Jul 2019 · 2 mos

• Computational Biology & Bioinformatics

May 2018 – Jul 2018 · 2 mos

• Worked at ITC's largest manufacturing unit in Bangalore on reducing key quality defects (Loose Shorts & Loose Ends).
• Adopted intensive Data Driven approach to identify Pain areas in End-to-End Manufacturing causing defects
• Identified and Established Key Control Levers in manufacturing which would reduce quality defects
• Validated protocols and manufacturing interventions leading to a reduction of 28.8% in the fallout of Loose Shorts in the high revenue Segments

Feb 2018 – Aug 2019 · 1 yr 6 mos · Kharagpur I, India

• Authored Conference Paper titled “Combining Pixel Selection with Covariance Similarity Approach in Hyperspectral Face Recognition” accepted in the 44th Annual Conference of the IEEE Industrial Electronics Society
• Authored Conference Paper titled “Fast Linear Unmixing of Hyperspectral Image by Slow Feature Analysis and Simplex Volume Ratio Approach” accepted in the 39th Annual IEEE Geoscience and Remote Sensing Society symposium
• Authored Journal Paper titled “Library Aided Bilinear Unmixing of Hyperspectral Image using Subspace Clustering and Multistep Pruning” accepted in Journal of Applied Remote Sensing

Dec 2017 – Jan 2018 · 1 mo · Pune, Maharashtra, India

• Successfully delivered two projects during a 45 day period earning appreciation from the General Manager, Pune India Technology Center, Schlumberger.
• 1. Migration of SAS and R Codes to PySpark for Resource Allocation
• Reduced Turn Around Time (TAT) in providing Predictions for Resource Allocation predictions
• Reduced Prediction frequency from 15 days to 1 day enabling daily predictive ability
• 2. Exploration of clustering Accidents and Work Incidents
• Led the foundation for grouping key Work Incidents based on clustering algorithms
• Obtained reasonable clustering accuracy in Incident grouping
• Reduced Manual Intervention in Incident grouping thereby leading to lower redressal response time

Aug 2017 – Jan 2018 · 5 mos · Indian Institute Of Technology Kharagpur

• Writing and creating content for LinkedIn’s publishing platform
• Discovering promising writers and unheard student voices, and promoting their content on LinkedIn
• Working with a LinkedIn News Editor to set goals, pitch post ideas, and edit content
• Represent the college campus and help to bring even more #StudentVoices to the LinkedIn platform.

May 2017 – Jul 2017 · 2 mos · Saharanpur Area, India

• 1. Software Automation of In-House systems: Designed and developed a novel Statistical Process Control application
• Developed Shewhart Chart, Cumulative Sum and Exponentially Weighted Moving Average modules to analyse process parameters
• Developed Quality Control Protocol (QCP) Adherence along with Alert Feedback and Logging modules to monitor QCP adherence as well as enable logging and monitoring of alert data
• Enabled Real Time Shop Floor Monitoring, Analysis and Correction of Quality parameters leading to improved quality scores in production
• Project to be taken up as a divisional level project in the future
• 2. Shop Floor Quality Index: Designed a new quality metric for analysing quality scores on a machine-wise level
• Enabled Quantitative Monitoring of Machine Health and Performance alongwith accurate prediction of origin of quality defects
• 3. Study of Moisture Content Drop in Cut Tobacco: Analysed Moisture Drop and it's dependence on Temperature and Relative Humidity
• Obtained a strong regression between Moisture Content Drop and Ambient Relative Humidity in Primary Manufacturing Department
• Enabled Intelligent Setting of Moisture Content Targets at Ex-KLD to obtain target moisture content value at Ex-Packer
• Received a Letter of Recommendation from the Production Manager for Excellence in the three projects.

Aug 2016 – Jul 2017 · 11 mos · IIT kharagpur

• Established in 2015 under the able agile of the Dean of Alumni Affairs and International Relations, the International Relations Cell has a clear cut objective of improving the ranking of IIT Kharagpur on the International Front.
• With ushered energy and renewed enthusiasm, the Cell concentrates on giving International Students and Faculty an experience at IIT Kharagpur that they are going to remember forever. We have already kickstarted work on many initiatives such as the Semester Exchange Program, Foreign Training Program as well as the International Summer Research Program. We intend to maximise awareness about the current collaborations and tie-ups that IIT Kharagpur has with other renowned International Universities while fostering the improvement in the quality of MOUs (Memorandum of Understanding) signed by IIT Kharagpur. Very soon, the International Relations Cell is going to be the springboard for the students in and outside IIT Kharagpur to achieve a Globally Diversified Classroom Experience.
• Key Accomplishments:
• Coordinated the Content Development Team which played a crucial role in International Branding of IIT Kharagpur
• Acted as Brand Ambassadors of Institute by facilitating MoU signing and Foreign Exchange Agreements with International Universities
• Officializing the Foreign Research Internship process and collaborating with CDC, IIT Kharagpur to set up the Foreign Training Portal
• Worked on Outbound Research Internships Networking with 5000 international professors under FTP
• Officializing the Semester Away Program (SAP) for semester exchange in collaboration with Dean UGS and Dean PGS with credits
• transfer to IIT Kharagpur for the first time after approval from the Institute Senate
• Analyzing and fostering the Improvement of the health of MoUs presently signed with IIT Kharagpur
• Organized Seminars on SAP (500 Attendees), Foreign Training (200 Attendees), MS & PhD (200 Attendees)

Mar 2016 – Aug 2016 · 5 mos · IIT kharagpur

• Alive Home Technologies is a start-up that innovates cutting-edge IoT solutions to deliver cost effective Home Automation products
• Developed a fully functional Scalable and Secure Cloud Server from scratch
• Learnt about Cloud deployments with exposure to Server Backend and designed the Database Schema
• Used multiple programming tools such as Python, AutoBahn WS and MongoDB.
• Key Learnings: Startup Exposure, Server and Database Setup, Ability to meet challenging deadlines,Grasping new concepts rapidly