Headline

Data Scientist - Pythonista - Data - ML

About

Passionate and skilled Machine Learning and Data Science Enthusiast experienced in Python development and dedicated to leveraging data science techniques to drive actionable insights. Proficient in data preprocessing, feature engineering, and model evaluation, with expertise in Python libraries (TensorFlow, Keras, scikit-learn) for efficient algorithm implementation. Committed to continuous learning and staying up-to-date with advancements in the field. Seeking opportunities to contribute to impactful projects and collaborate with innovative teams. Programming: Python, MySQL, C, C++, Dart Lib/Frameworks, Deploy & Other : Numpy, Pandas, Matplotlib, Seaborn, Statistics, Tensorflow, OpenCV, Scikit-Learn, Streamlit, Flask, HuggingFace, Langchain, OpenAI API, Heroku, Shell Scripting, PL/SQL, SQL, NoSQL, SDLC, OOP.

Location

Greater Bengaluru Area

AI stack

claude code

hugging face

langchain

langgraph

ollama

openai

Work experience

Data Scientist - I at EY, Sep 2025 - Present · 1 yr 2 mos, Bengaluru, Karnataka, India

Research Development Software Engineer at Sekyurity AI, Sep 2023 - Aug 2025 · 2 yrs, Bengaluru, Karnataka, India, Worked in building NiKi, the world's most advanced CyberAI agentic platform for securing enterprise and cloud Infrastructures.

Machine Learning Intern at Globussoft Technologies, Sep 2022 - Aug 2023 · 1 yr, Bengaluru, Karnataka, India, 𝗣𝗿𝗼𝗷𝗲𝗰𝘁 𝟭: 𝗘𝗺𝗮𝗶𝗹 𝗜𝗻𝘁𝗲𝗻𝘁 𝗖𝗹𝗮𝘀𝘀𝗶𝗳𝗶𝗲𝗿 [𝗦𝗲𝗽𝘁 𝟮𝟬𝟮𝟮 - 𝗝𝗮𝗻 𝟮𝟬𝟮𝟯] 𝗢𝗯𝗷𝗲𝗰𝘁𝗶𝘃𝗲: Built an ML model to discern email conversation intent. - Performed Intent Classification on Enron Copora Email Dataset by labelling it with the Weak Supervision Technique, resulting in an f1 score of 0.9752. - Leveraged the pretrained bert model of Deeppavlov for the Named Entity Recognition from the given messages or texts. 𝗣𝗿𝗼𝗷𝗲𝗰𝘁 𝟮: 𝗔𝗱 𝗖𝗮𝘁𝗲𝗴𝗼𝗿𝗶𝘇𝗮𝘁𝗶𝗼𝗻 [𝗙𝗲𝗯 𝟮𝟬𝟮𝟯 - 𝗔𝘂𝗴 𝟮𝟬𝟮𝟯] 𝗢𝗯𝗷𝗲𝗰𝘁𝗶𝘃𝗲: Implemented an Ad Categorization Filtering in PowerAdSpy - Built an Ad Categorization Model, categorizing the ads based on websites ad context with the accuracy of 85%

Data Science Intern at FloData Analytics, Jul 2021 - Oct 2021 · 4 mos, Delhi, India, 𝗣𝗿𝗼𝗷𝗲𝗰𝘁 𝗡𝗮𝗺𝗲: 𝗢𝗵𝗶𝗼-𝗢𝗖𝗥 [𝗝𝘂𝗹 𝟮𝟬𝟮𝟭 - 𝗢𝗰𝘁 𝟮𝟬𝟮𝟭] 𝗢𝗯𝗷𝗲𝗰𝘁𝗶𝘃𝗲: To increase the number of clients of a chiropractor living in Ohio US. - Developed an automated system to extract valuable data from US accident records (PDF format) in multiple counties, uploading it to AWS S3. - Performed text extraction on vector images with help of fitz library in Python and got accuracy of about 95%. - Performed image processing and OCR by leveraging OpenCV on raster images and extract text with the help of Pytesseract and got accuracy of about 85%.

Education

Bachelor of Technology - BTech, Electronics and Communications Engineering, Bhilai Institute of Technology (BIT), Durg

Senior Secondary School Certificate 12th, Science Stream, PCM, kendriya vidyalaya

Public links

github: https://github.com/Shivam-Shrivastav

leetcode: https://leetcode.com/shivamshrivastava1810

shivam-shrivastav.github.io: https://shivam-shrivastav.github.io/