Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I’m a data scientist and software developer who loves turning messy data into practical insights and scalable systems. I enjoy building end-to-end ML pipelines, from data gathering and preprocessing to model deployment and monitoring, across Python, Spark, and cloud platforms. My work spans robotics, finance, and consumer apps, with hands-on experience in computer vision, NLP, time-series forecasting, and anomaly detection. I thrive in collaborative teams and enjoy translating complex problems into clear, impact-driven solutions.…I’m a data scientist and software developer who loves turning messy data into practical insights and scalable systems. I enjoy building end-to-end ML pipelines, from data gathering and preprocessing to model deployment and monitoring, across Python, Spark, and cloud platforms. My work spans robotics, finance, and consumer apps, with hands-on experience in computer vision, NLP, time-series forecasting, and anomaly detection. I thrive in collaborative teams and enjoy translating complex problems into clear, impact-driven solutions.

Zhuotong Sheng

Data Scientist, Full Stack Developer, Developer, +2





I’m a data scientist and software developer who loves turning messy data into practical insights and scalable systems. I enjoy building end-to-end ML pipelines, from data gathering and preprocessing to model deployment and monitoring, across Python, Spark, and cloud platforms. My work spans robotics, finance, and consumer apps, with hands-on experience in computer vision, NLP, time-series forecasting, and anomaly detection. I thrive in collaborative teams and enjoy translating complex problems into clear, impact-driven solutions.…I’m a data scientist and software developer who loves turning messy data into practical insights and scalable systems. I enjoy building end-to-end ML pipelines, from data gathering and preprocessing to model deployment and monitoring, across Python, Spark, and cloud platforms. My work spans robotics, finance, and consumer apps, with hands-on experience in computer vision, NLP, time-series forecasting, and anomaly detection. I thrive in collaborative teams and enjoy translating complex problems into clear, impact-driven solutions.

Available to hire

I’m a data scientist and software developer who loves turning messy data into practical insights and scalable systems. I enjoy building end-to-end ML pipelines, from data gathering and preprocessing to model deployment and monitoring, across Python, Spark, and cloud platforms.

My work spans robotics, finance, and consumer apps, with hands-on experience in computer vision, NLP, time-series forecasting, and anomaly detection. I thrive in collaborative teams and enjoy translating complex problems into clear, impact-driven solutions.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Language

English

Fluent

Work Experience

Research Assistant at Brown Intelligent Robot Lab

September 1, 2025 - Present

Developed a computer vision pipeline for one-shot robotic imitation learning. Used Vision-Language Models and latent feature matching (PCA + Clustering + Cosine Similarity) to achieve one-shot object part detection, improving accuracy to 85%. Integrated part segmentation with LLM-prompted recognition to automate semantic part identification. Built a 3D perception module to generate point clouds with RGB-D data and deployed the pipeline on a physical robot arm via ROS2.

Data Scientist Intern at Rocket Mortgage

May 1, 2025 - August 31, 2025

Developed ML pipelines in PySpark and SQL on AWS with 100M+ records to identify high-intent refinance customers. Achieved 83% ROC-AUC and 60% recapture rate. Performed EDA and preprocessing, trained and tuned XGBoost, Random Forest, SVM and LightGBM; standardized experiment logging and evaluated models in MLflow. Collaborated with MLE team on deployment and monitoring and implemented automated drift detection and retraining logic, reducing post-deployment performance degradation by 30%.

Marketing Data Scientist Intern at Soul App (International Growth Department)

December 1, 2023 - April 30, 2024

Developed linear regressions to quantify campaign effectiveness; defined KPIs and feature drivers, lifting conversion rate from 0.2% to 0.5%. Deployed an Auto-regressive time-series model to forecast daily active users and established an automated anomaly-detection framework. Architected an automated data pipeline integrating SQL databases with Google Spreadsheets via API and JavaScript, reducing manual data work by 20%.

Data Engineer Intern at RBS

June 1, 2024 - August 31, 2024

Designed ETL pipelines in Snowflake to process 1M+ building usage and occupancy records, applying a STAR schema to improve accessibility and reduce processing time by 30%.

Marketing Analyst Intern at Jiazuo Design Inc.

October 1, 2020 - April 30, 2021

Conducted A/B testing on the App Jia Art; used causal inference to optimize campaign impact, increasing customer engagement by 10%. Applied clustering to segment high-potential customer groups, forecasting a 10%+ increase in foot traffic, and contributed to a pop-up launch with a 20% profit margin.