Exploring Exciting Opportunities | Senior ML Engineer @ Docquity| LLM Expert | Solving RAG(LLM) based Use-cases| Healthcare|ML|Data Science|NSIT'20
8 Years of Experience
Bengaluru, Karnataka, India
-
-
Not Available
I am a data scientist interested in taking on large and challenging problems, finding useful information hidden in the data, and using these insights to drive improvements via creative solutions. Established track record of combining software engineering, mathematical/statistical data analysis, and machine learning. I write high-performing code and scripts for organizations to help them generate more revenue, identify areas of investment, isolate redundancies, and automate processes. anupampoddar1@email.com PERSONAL DOSSIER Geekforgeeks profile: https://auth.geeksforgeeks.org/user/champgamy/practice/ Codechef profile: https://www.codechef.com/users/anupamp11 Leetcode profile: https://leetcode.com/anupamking01/ Hackerrank profile: https://www.hackerrank.com/anupampoddar1997 Github link: https://github.com/anupamking01/ research paper link: https://drive.google.com/drive/folders/1TDZF0R6WqRZVSH469GOfmTlANqfp4A-X?usp=sharing Certificates link: https://drive.google.com/drive/folders/1Q9E4g6cW3UR6QDN-dkId6tt_08j53bYU?usp=sharing
Docquity, SaaS/Cloud Product, Hospital & Health Care
Vahak
Orange Business Services
Docquity, Vahak, Orange Business Services, Nagarro, Pinna.ai, Coding Club, Netaji Subhas Institute of Technology, Edgistify
Job Title : Senior ML Engineer
Company name : Docquity
Period : November 2023 - Present
Summary : Working on LLMS, enhancing and scaling Embedding based Document search method(Retriever Augmented Generation) and finetuning with Knowledge graph and key-word search.
Pdf parsing into chunks using open source pdf parsers.
POCs around Bio-bert,Sci-spacy and many other hugging face open source models for bio-medical entity extraction like disease, gene,drug etc.
Entity ranking with the help Pubmed bert,Bio-bert embeddings for bio-medical context.
Creation of dataset using techniques like Paraphrasing,Summarization.
Used Prompt Engineering,Lang chain and open-ai api for answer generation.
Skills - LLMs, NLP, Fine-tuning, Knowledge Graph,RAG,Chat PDF,Gen AI,Hugging face, BERT,GPT,open-ai,Neo-JS,Vector db,Pinecone,LLama Index, Llama2,Prompt Engineering.Langchain,Pubmed etc.
Location : Gurugram, Haryana, India
Job Title : Data Scientist
Company name : Vahak
Period : November 2022 - November 2023
Summary : * Automating the cashback system for our App using the OCR techniques:
- Reduce manual Eway Bill Verifications by more than 60%. - Extract RC Verified Lorry Numbers & GST numbers
- Improved Quality by Identifying duplicates and Qrcode verification
- POCs and implementation on top of AWS Textract and AWS Recognition
-created a pipeline for creating a dump of EWay bills -Figured out pipeline from Ec2-machine to S3 bucket back and forth -figured out fraudster with Qrcode duplicate analysis, people uploading more than 100 same Eway bills. - did well within the stipulated time including deployment.
* Pipeline for Knowlarity call recordings data collection :
-Call Recordings collection of around 50,000 calls -retrieved calls separately for potential fraud users and Power users to analyze them separately -Done it in a shorter span due to time constraints as our services were stopped.
* Call recording transcription analysis(Data Analysis):-
Identified patterns of fraudsters by a thorough analysis of Fraud calls, Analyzed more than 100 calls. -figured out the hypothesis of a fraudster.
* Script to identify inflow issues in important production tables:
-Identifying the inflow issues automatically and mail is sent to the DevOps team to rectify it in real-time. - Script was created and scheduled within a day.
* pipeline for the big query to redshift using Gcloud SDK without Gcloud API.
* Masking portion of Aadhar card number using objection detection model, used YOLOv8 as the model architecture and trained it for 2500 annotated datasets. achieved 100% map for the test set.
Location : Bangalore Urban, Karnataka, India
Job Title : Machine Learning/Data Science Engineer
Company name : Orange Business Services
Period : August 2021 - November 2022
Summary : OCR techniques to extract text from warning/error screenshots ongoing applications and applying NLP techniques to remove unwanted symbols and terms and processing it for AUTO heal application to identify the error and fix itself.
Creating rest API with the help of flask for predicting diseased olive crops using YOLO model, from labelling and training the model to predict it.
Building an Application to automate Jira test case using techniques custom NER and meaning generation with pos tagging[poc] and development & authentication of the complete application using flask API.[OBS]
Location : Gurugram, Haryana, India
Job Title : Software Developer - ML
Company name : Nagarro
Period : January 2021 - August 2021
Summary : Performed sentiment analysis of website texts and built a web scraper using Python, which helped finetune the market-strategy
Developed a loan default model using various ML algorithms on a loan book ; achieved best precision scores .
Performed extensive documentation of Elasticsearch and implemented complex queries and aggregations to form summaries.
Location : Gurugram, Haryana, India
Job Title : AI/ML Developer (Intern)
Company name : Pinna.ai
Period : July 2020 - January 2021
Summary : Creating End to End Pipeline of the current model, Including new Functionalities for product.
Increased accuracy of Speech recognition model.
Creating End to End Pipeline of the current model, Including new Functionalities for product
One word Detection Engine(Keras Model) [PINNA.AI](9 months)
Location : United States
Job Title : Coding Mafia
Company name : Coding Club
Period : September 2019 - August 2020
Summary : Mentored Students on Problem-solving, Data Structures in C++.
Location : New Delhi Area, India
Job Title : Student Researcher
Company name : Netaji Subhas Institute of Technology
Period : August 2016 - August 2020
Summary : *Face Recognition Attendance System:
-The project is a minor project based on OpenCV and Python that aims to create an attendance system using face recognition technology. The system is designed to recognize faces based on parameters such as the distance between two eyelids, cheekbones, etc. The project is useful for colleges and organizations that require a faster and more efficient attendance system.
*Skillset Ontology:
-The project is a research paper that proposes a machine learning-based ontology for segregating student projects based on technical and non-technical skills. The project aims to facilitate mutual learning among students by matching them with projects that complement their skillset. The project utilizes different aspects of machine learning such as NLP, NLTK, formal concept analysis, and web scraping using Selenium, BeautifulSoup, and Mechanize.
*Smart Home Automation using IOT-Raspberry Pie:
-The project is a major project that focuses on creating a smart home automation system using IoT and Raspberry Pi. The system allows users to control various devices in their home remotely through a mobile application.
*Chatbot & Pong Game using Turtle module, Snake game (pygame module), DRS system:
-The project is a collection of minor projects that includes a chatbot, Pong game using Tur
Title : Mastering OCR end to end
Period : August 2022 - Present
Summary : UC-29841349-6674-463b-b0d1-488e864a26e0, udemy.com, https://www.udemy.com/certificate/UC-29841349-6674-463b-b0d1-488e864a26e0/
Issuing Authority : Udemy
Title : Communicating Values
Period : August 2021 - Present
Summary : linkedin.com, https://www.linkedin.com/learning/certificates/498cd9412da02440c42d40cc4bc2db4b27b4c2f0078f7b03bb3ee773e490709d?trk=backfilled_certificate
Issuing Authority : LinkedIn
Title : Introduction to GPT-3: A Leap in Artificial Intelligence
Period : August 2021 - Present
Summary : linkedin.com, https://www.linkedin.com/learning/certificates/cd0775478f355a7168ed4194dd7ad4fcf8c9d9782871b4b4117f3a50ba8d5860?trk=backfilled_certificate
Issuing Authority : LinkedIn
Title : Basic Problem Solving
Period : January 2021 - Present
Summary : hackerrank.com, https://www.hackerrank.com/certificates/53402fbb3bdc
Issuing Authority : HackerRank
Title : Java
Period : January 2021 - Present
Summary : hackerrank.com, https://www.hackerrank.com/certificates/90e7fe43b7f7
Issuing Authority : HackerRank
Title : Learning AngularJS 1
Period : January 2021 - Present
Summary : linkedin.com, https://www.linkedin.com/learning/certificates/c70ecd83b0952da5ec7a4d3c478dda57b319fa52a2f04eb46775df709cd3c95b?trk=backfilled_certificate
Issuing Authority : LinkedIn
Title : Building Deep Learning Applications with Keras 2.0
Period : June 2020 - Present
Summary : linkedin.com, https://www.linkedin.com/learning/certificates/b632677cbbedc684b249b0cae0857037aeb1fae63effb3fdbffe839d4180b732?trk=backfilled_certificate
Issuing Authority : LinkedIn
Title : Neural Networks and Convolutional Neural Networks Essential Training
Period : June 2020 - Present
Summary : linkedin.com, https://www.linkedin.com/learning/certificates/bed4eb0a4099c10e9adb4d41a8e3530d506ea9be4829ba95d5b792631544345a?trk=backfilled_certificate
Issuing Authority : LinkedIn
Title : Artificial Intelligence Foundations: Thinking Machines
Period : April 2020 - Present
Summary : linkedin.com, https://www.linkedin.com/learning/certificates/02f1d994c7c4d45d5e61091c8af4a13fb1996152a85a9e5bd331eb417dd1c0c6?trk=backfilled_certificate
Issuing Authority : LinkedIn
Title : Douglas Kirkland on Photography: Natural Light Portraiture
Period : April 2020 - Present
Summary : linkedin.com, https://www.linkedin.com/learning/certificates/c098f1035f29f701972e8a8b31d67586edd64e0e543fa8979ab1ddf7aea43c4e?trk=backfilled_certificate
Issuing Authority : LinkedIn
Title : Advanced Face Recognition
Issuing Authority : LinkedIn
Title : Coding Mafia
Issuing Authority : Coding Club
Title : Python, C,C++,CSS,HTML,JQuery,JavaScript
Issuing Authority : SoloLearn
Title : UC Campus Ambassador
Issuing Authority : UC Browser
Title : Extraction of Technical and Non-technical Skills for Optimal Project-Team Allocation
Publisher : Springer International Publishing
Publication time : 2020
Summary : Project portfolio management (PPM) is a crucial subject matter in academics t
English (Full Professional), Hindi (Native Or Bilingual)
Show More