Information Systems Data Scientist

Agash Uthayasuriyan

+1-617-***-**** - ad5v8q@r.postjobfree.com - LinkedIn - GitHub - Portfolio - Availability: May 2024 - Dec. 2024 EDUCATION

Northeastern University Boston, MA, USA

Masters of Science in Information Systems Sept. 2023 - May 2025 Amrita Vishwa Vidyapeetham Coimbatore, India

Bachelor of Technology in Electrical and Computer Engineering Jun. 2019 - Jun. 2023 ACADEMIC PROJECTS

News Collector & Summarizer [GitHub] Apr. 2024

Tech Stack: Beautiful Soup, OpenAI, Snowflake, GCP, Kafka, MongoDB, FastAPI, Streamlit, Airflow, SERP API

• Designed a scalable end to end Big Data pipeline, deployed on GCP VMware with continuous integration and continuous deployment (CI/CD), to curate personalized daily news across 23 categories

• Utilized pandas, spaCy NLP to extract keywords for news categorization, enabling 30% faster content discovery

• Orchestrated integration of 5 DAGs via Apache Airflow and facilitated Kafka real-time data streaming for keyword notifications, resulting in a user-friendly application powered by FastAPI and Streamlit Real-Time Android & iOS Chat Application [GitHub] Oct. 2022 Tech Stack: Flutter, Android Studio, Google Firebase, Dart, iOS, Swift, XCode

• Built a mobile development solution for Android and iOS platforms with a group chatting feature using Flutter

• Used Google Firebase to authenticate and authorise users, store chat history, ensuring high security & reliability RAG Application - Chat with any Website [GitHub] Feb. 2024 Tech Stack: OpenAI Embeddings, OpenAI GPT, Langchain, Pinecone, Docker, Streamlit

• Created a RAG Application leveraging web scraping techniques to extract contents from any given website and vectorizing them into a 1536-dimension for storing in a vector database

• Utilized Langchain, semantic search, and OpenAI GPT-3.5 Turbo LLM, to have a conversation with the user WORK EXPERIENCE

Amrita School of Computing Coimbatore, India

Data Scientist Jun. 2022 - Jun. 2023

• Led data science research team to develop two innovative hybrid frameworks integrating Machine Learning and Artificial Intelligence algorithms, enhancing Social Network link prediction by 15%

• Conducted analysis on 8 large datasets and A/B Hypothesis testing to validate results and obtain insights

• Exhibited strong oral and written communication skills by producing 6 research papers outlining key findings Mekala Transports Chennai, India

Data Analyst Jan. 2022 - May 2022

• Transformed unstructured data into structured tables in STAR schema, reducing manual processing time by 25%

• Implemented data cleaning ensuring data quality, normalization, and applied over 50 check constraints, stored procedures, triggers, views, encryption, non-clustered indexes, and UDFs in RDBMS to optimize CRUD operations

• Developed interactive Tableau Business Intelligence (BI) dashboard, unveiling data trends across multiple KPIs, leading to a 20% enhancement in data driven decision making TECHNICAL SKILLS

Programming Languages : SQL, HTML, JavaScript, Python Databases (SQL & NoSQL) : SQLite, MySQL, MongoDB, Oracle, MS SQL Server, Cassandra, PostgreSQL, MongoDB Data Services : Data Mining, Data Analysis, Data Pipeline (ETL, ELT, ETLT), Database design, Data Modelling Data Visualization & Data Analytics : Statistics, Matplotlib, Seaborn, Tableau, PowerBI, Alteryx Cloud Technologies : Snowflake, Databricks, GCP, Azure, AWS S3, EC2, Lambda, SQS, SNS, IAM Libraries : Pandas, NumPy, Scikit-learn, SciPy, Pyarrow, Pydantic, Pytest, Streamlit, Beautiful Soup, Selenium Tools : Airflow, Kafka, PySpark, Docker, CI/CD, Linux, FastAPI, Talend, Excel, PowerPoint, PowerApps, OneNote Certification : AWS Cloud Practitioner [Link]

PUBLICATIONS

• Social Network Link Prediction Using Differential Evolution Based Extreme Gradient Boosting Algorithm Link

• Performance Evaluation of Evolutionary Algorithms on Solving the Influence Maximization Problem Link

• Comparative Analysis on Genetic algorithm and Reinforcement Learning Link

Contact this candidate