Data Scientist

Rabina Khatiwada

***********@*****.*** LinkedIn: rabinakhatiwada GitHub: rabina302 Seattle, WA PROFESSIONAL SUMMARY

Results-driven Data Scientist with 4 years of experience in developing, deploying, and maintaining machine learning models to solve complex business problems. Skilled in leveraging big data technologies, modern AI frameworks, and statistical analysis to drive actionable insights. Adept at translating business needs into data science solutions and effectively communicating insights to technical and non-technical stakeholders. Passionate about innovation and continuous improvement in data science methodologies. PROFESSIONAL EXPERIENCE

Data Scientist

Srimatrix Inc Feb 2024 – Present

● Leveraged statistical programming languages like R and Python to develop predictive models and analyze structured and unstructured data, enhancing decision-making.

● Designed and executed complex SQL queries to extract, manipulate, and analyze data from relational databases, improving data-driven insights and reporting accuracy.

● Experience with Apache Hadoop components such as HDFS, MapReduce, and YARN, and proficient in querying and processing big data using Hive and SQL-based solutions.

● Employed data parsing, manipulation, and preparation techniques to ensure data readiness and improve usability for modeling and reporting, while conducting comprehensive data cleansing and validation processes using ETL tools like Informatica. Artificial Intelligence Intern

Ametek Surface Vision May 2023 – Dec 2023

● Trained Tensorflow models using Keras with material surface images for defect detection, binary semantic segmentation, and edge tracking to use in manufacturing industries for quality check.

● Integrated trained models with existing classifier engine in C++ for inferencing after converting them using either TensorflowLite converter or Keras2cpp.

● Built a minimal Flask web application that schedules training jobs with data and parameters received from other services via MQTT topic. Live status is displayed by fetching it using WebSocket.

● Created WPF application using MVVM toolkit to identify newly connected camera’s IP address with UDP broadcast and to configure a new IP address.

Graduate Research Assistant

St. Cloud State University Feb 2022 – May 2023

● Conducted in-depth statistical analysis on large volumes of clients' data using SPSS and SAS, addressing complex research and business challenges.

● Collaborated with university researchers to design robust data models, apply advanced statistical techniques (e.g., regression analysis, ANOVA, hypothesis testing), and provide actionable insights that supported academic publications and cross-institutional projects.

● Partnered with external businesses to transform unstructured raw data into valuable insights by leveraging statistical methods such as clustering, time-series forecasting, and correlation analysis, driving evidence-based decision-making.

● Prepared detailed reports, visualizations (tables, graphs, and dashboards), and fact sheets that highlighted key findings, ensuring clarity and accessibility for both technical and non-technical stakeholders. Software Engineer

Terakoya Academia Inc Aug 2020 – Nov 2021

● Researched and trained machine learning models using Python libraries (NumPy, Pandas) and frameworks (TensorFlow, Keras, PyTorch, SpaCy) to integrate into larger data annotation systems for the Japanese language.

● Utilized Amazon Sagemaker to streamline the development, training, and deployment of machine learning models for diverse contexts of Text Classification, Image Classification, and Named Entity Recognition.

● Contributed to the company website by implementing React Components and Hooks. Setup CI/CD pipelines using GitHub Actions to deploy the latest build to AWS Amplify after each commit.

● Championed adoption of modern engineering practices in the team like tracking and increasing code coverage, collaboratively documenting coding and testing guidelines, occasional learning days/events, etc. EDUCATION

St. Cloud State University

MS in Computer Science CGPA: 3.67 Jan 2022 –May 2024 Relevant courses: Natural Language Processing, Operating System, Object Oriented Software Development, Data Structures, Computer Architecture.

SKILLS

Programming Languages: Python, R, Java, Bash

Tools and Frameworks: TensorFlow, PyTorch, Keras, spaCy, Flask, Docker, GitHub Actions, REST API, Kafka Big Data & Cloud: AWS (S3, Sagemaker, EC2, Lambda, Amplify), Apache Hadoop (HDFS, Hive, MapReduce), Databricks Data Processing & Visualization: NumPy, Pandas, Matplotlib, SPSS, Minitab Databases: MySQL, MongoDB

CERTIFICATIONS

● Microsoft Azure Machine Learning Fundamentals

● Advanced Python: Working with Data

RESEARCH AND PROJECTS

● Fake News Detection System: Developed deep-learning models (LSTM, GRU, BioBERT) to detect fake news in COVID-19 articles by extracting biomedical information using MetaMap and SciSpacy, as part of Master thesis.

● Material Surface Inspection: Integrated vision models into manufacturing pipelines to detect material defects and enhance quality assurance processes.

Contact this candidate