Master of Science in Data Science

GPA - 3.90/4.0

Bachelor of Technology, Computer Science and Engineering

CGPA - 8.4/10.0

Graduate Teaching Assistant

Course: Data Intensive Computing

Responsibilities:
• Mentor students with programming assignments, projects, and implement solutions using Big Data tools such as Hadoop, Spark, ML algorithms, and databases, etc.
• Develop and administer weekly quizzes to assess student understanding and progress.
• Conduct demonstrations and workshops to illustrate practical applications of Big Data tools and techniques.
• Collaborate with the professor in the grading process and provide valuable insights for course improvement.

Machine Learning Engineer

Remote – Bangalore, India
Platform, Data, and ML Engineering
• Collaborated with 4 domain experts to create ML models for Lung Cancer detection and stage prediction
• Engineered over 250 features from large-scale clinical datasets using PySpark, S3, and Glue jobs
• Productionalize end-to-end Machine Learning workflows using Sagemaker pipelines
• Transitioned data pipelines from Step Functions to Airflow, expanded integrations beyond AWS
• Addressed compliance issues for 4 AWS services, improved security using Boto3, and Lambda

Data Engineer

Bangalore, India
Data Science and Engineering
• Implemented data-centric solution for optimizing out-of-home ads, using geospatial data for real-time analytics
• Deployed ETL processes to ingest data from 4 vendors into S3 which enhanced accessibility by 30%
• Orchestrated 10+ data pipelines and developed algorithms to generate audience insights and impressions
• Scaled platform to handle 500+ GBs of data, managed 10+ billion observations every week
• Discovered and resolved 3 crucial data quality issues using Deequ, fostered credibility and predictive accuracy
• Built 5+ impactful Superset dashboards using SQL and Athena, elevated campaign planning for US & UK region
• Tailored RASA chatbot for top Indian transport firm, refined core NLP features – NEL and intent ranking

Trainee Software Developer - R&D

Bangalore, India
Data Analysis, Machine Learning, and Deep Learning
• Designed a system to block IP addresses/domains on Checkpoint Firewall based on score threshold
• Analyzed unstructured real-time firewall logs, and created 2 attributes to determine severity levels
• Developed a Neural Network to calculate risk score of incident logs using Python and TensorFlow
• Automated repetitive SOC analysts’ tasks using APIs in Python, leading to 5x faster incident response time