Python, Spark, ETL, SQL, AWS, PowerBI, Tableau, Machine Learning

SAI MANIHAR REDDY NALLAGONDU

P: +1-213-***-**** ************@*****.*** https://www.linkedin.com/in/sai-manihar-reddy-nallagondu/

WORK EXPERIENCE

CHILDREN’S HOSPITAL LOS ANGELES Los Angeles, CA

Data Scientist Research Assistant Sep 2023 – Jul 2024

● Optimized multi-core High-Performance Computing (HPC) environments by implementing parallel processing techniques

that reduced analysis time by approximately 60 hours per month while maintaining compliance with all regulatory standards.

● Developed innovative methodologies for analyzing large-scale single-cell RNA datasets; executed clustering algorithms

leading to the identification of novel therapeutic targets & protein interactions used by researchers over a six-month period.

TIGER ANALYTICS Chennai, India

Senior Software Engineer Aug 2021 – Nov 2022

● Devised an innovative Feature extraction project in Python using pattern recognition and similarity search, analyzed heroic

SKUs resulting product enhancements and capturing target markets, boosting sales through strategic decisions.

● Engineered robust data normalization processes across 12 web-sourced tables utilizing Python and SQL techniques;

ensured consistency while preserving compliance with high standards of data quality which is utilized by 6+ teams.

● Collaborated with global teams of data scientists and product managers, utilizing Jira for task tracking and effective

communication, to align project requirements with business goals and deliver products that meet client expectations.

● Refactored existing codebase while automating data pipelines through Jenkins and Python, leading to enhanced performance

for over 8 projects; cut down on manual processing time by an impressive margin of 60% for specified refresh cycles.

Data Analyst Aug 2020 – Jul 2021

● Overhauled the structure of global inventory data processes by conducting detailed ad-hoc analyses and optimizing SQL

queries; realized a substantial 70% decrease in query execution duration alongside improving forecast precision by 25%.

● Transformed global e-commerce promotional data across 256 product categories using Python and Snowflake; crafted a

comprehensive PowerBI dashboard that enabled stakeholders to make informed decisions based on actionable sales insights.

● Conducted in-depth data analysis on vast datasets exceeding 5TB with Python, AWS S3 & Spark while querying Hive

databases; delivered comprehensive trend reports identifying key patterns that supported decision-making processes.

PROJECTS

LANDMARK CLASSIFICATION USING DEEP LEARNING

Designed a landmark and category classification model using transfer learning (VGG26, EfficientNetB0) on TensorFlow,

leveraging GPU acceleration and data augmentation to achieve 93% accuracy with limited image data.

TA COPILOT USING LLMs GENAI

Engineered an LLM based chatbot integrating with Lang Chain & vector database for efficient handling of lecture notes, Q&As

and lecture video transcripts, boosting conversational response capabilities and reducing academic staff workload by 70%.

CREDIT CARD FRAUD DETECTION

Engineered a predictive fraud detection model employing XGBoost and Random Forest, achieving 83% accuracy through

advanced sampling techniques, feature selection, cross validation and hyperparameter tuning on imbalanced datasets.

STATISTICAL ANALYSIS OF FOOD ORDERING BEHAVIORS

Conducted comprehensive regression analysis with Hypothesis Testing to assess factors affecting online food ordering habits

among 500 USC students, achieving a power level of 72% and isolating critical determinants influencing preferences.

RECOMMENDATION SYSTEM FOR USC DATA MINING COMPETITION

Implemented item-based and model-based collaborative filtering techniques on Yelp dataset using Spark and Python, integrating

results with weighted averages to optimize recommendations & achieved an RMSE of 97.63, enhancing user satisfaction.

SKILLS

Programming: Python, Apache Spark, R, Java, JavaScript, D3.js

Databases: Snowflake, SQL, NoSQL, MongoDB, DynamoDB, HiveQL, Firebase

Other: AWS, PowerBI, Tableau, ETL, Statistics, Agile Methodology (Jira), Machine Learning, Hadoop

EDUCATION

UNIVERSITY OF SOUTHERN CALIFORNIA Los Angeles, CA

Masters/MS in Applied Data Science Dec 2022 - Dec 2024

SRM INSTITUE OF SCIENCE AND TECHNOLOGY Chennai, INDIA

BTech in Computer Science Engineering Jul 2016 - Jul 2020

Contact this candidate