data scientist

PATHURI NAGA MANVITHA

Detroit, MI, ***** Relocatable 346-***-**** ad5r51@r.postjobfree.com LinkedIn GitHub SUMMARY: Versatile Software Engineer with expertise in data analysis, API development, and cloud migration. Skilled in Python, C++, JavaScript, and various frameworks. Proven ability to enhance system performance and manage large-scale data processing. Currently pursuing a M.S. in Computer Science with a focus on AI and distributed systems. Experienced in improving agricultural processes and facilitating government project collaborations. EDUCATION

Wayne State University, Detroit, MI August 2023 – May 2025 (Expected) Master’s in computer science, GPA: 3.60

• Key Courses: Artificial Intelligence, Distributed systems, Data mining, Intelligent Systems GITAM University, Hyderabad, TN July 2019 – May 2023 B. Tech in Computer Engineering, GPA: 3.80

• Key Courses: Computational Statistics, Statistical Inference, OS, OOP, DBMS, IOT SKILLS

Programming Languages: C++, Python, JavaScript, C#, Java, Bash, R Frameworks & Libraries: Node.js, Angular, React.js, Django, Selenium, Rails, Spring Boot. Databases: SQL Server, MongoDB, DynamoDB, MySQL, Elasticsearch, Postgres Tools & Technologies: Snowflake, PowerBI, Tableau, Git, Jenkins, GitHub, Jira, Hadoop, Kafka, Jupyter EXPERIENCE

Software Engineer June 2022 – May 2023

Baker Tilly Pvt Ltd. Hyderabad, India

• Facilitated connections between farmers and consultants in government projects, enhancing collaboration and resource access.

• Analyzed soil data collected from farmers, performing A/B tests that resulted in a 20% improvement in decision-making and optimization of agricultural processes.

• Collaborated with a research team to process data and develop a website using AngularJS.

• Developed and maintained features for a data reliability monitoring application using Python and SQL, integrating DataBand’s Python SDK with various data monitoring tools to enhance pipeline visibility. Software Engineer Intern January 2022 – June 2022

FactSet Hyderabad-India

• Enhanced and maintained formula management products at FactSet.

• Improved the performance of the formula timing API by 30% through parallel processing.

• Developed an API logging platform to enable centralized logging for various team services.

• Managed and operated Elasticsearch clusters, handling billions of logs per day from multiple services.

• Contributed to the migration of the Central Logging Platform from an in-house solution to AWS Cloud. ACADEMIC PROJECTS

IDS with ML {Python, Scikit-learn, Snort, Seaborn}

• Trained various Machine Learning models on CIC-IDS 2017 dataset containing real world network flow data.

• Best Model classified whether packet stream is malicious or not. The model was also able to distinguish different types of malicious attack by 40%.

Big Five Personality Clustering {Python, Jupyter Notebook, Pandas, Scikit-learn}

• Conducted clustering analysis of Big Five Personality Traits with IPIP-FFM 2018 dataset.

• Applied K-means and Hierarchical clustering techniques for segmentation. Identified distinct patterns and enabled targeted interventions.

Automated Soil Data Analysis for Agricultural Optimization{Python,Matplotlib, MySQL}

• Developed a Python-based system to automate soil data collection from various sensors, improving data accuracy and reliability.

• Analyzed soil parameters (moisture, pH, temperature) using Python libraries and generated actionable insights

• Enabled data-driven agricultural decisions, leading to a 18% optimization in processes and improved yields.

Contact this candidate