Open to opportunities

Hemanth Sai

@hemanthsai

Message

Curious, impact-driven Data Scientist specializing in scalable ML, real-time analytics, and cloud-native pipelines.

United States

Message

What I'm looking for

I seek roles where I can build scalable ML and real-time analytics systems, collaborate cross-functionally, and advance MLOps and data-driven decision making.

I am a data scientist with 4.5+ years building and deploying scalable machine learning solutions, real-time analytics systems, and cloud-native data pipelines across cloud infrastructure, higher education, and customer operations.

I designed predictive models and forecasting systems (ARIMA, Prophet, XGBoost, LightGBM) that delivered measurable savings and operational improvements, built sub-second anomaly detection with Kafka and Spark Streaming, and automated model retraining using Airflow and SageMaker.

I collaborate closely with engineering and business stakeholders to translate needs into robust data strategies, optimize ETL and dashboard performance, and implement monitoring and MLOps practices that reduce manual intervention and speed decision-making.

Experience

Work history, roles, and key accomplishments

Current

Data Scientist

Current

Arthrex

Mar 2024 - Present (1 year 11 months)

Designed and deployed automated ML pipelines and time-series forecasting models (ARIMA, SARIMA, Prophet, XGBoost) to improve server demand prediction and pipeline performance; implemented model monitoring and retraining triggers integrated with AWS CloudWatch.

Python Pyspark AWS Sagemaker Apache Airflow XGBoost Time Series Tableau Git

Data Analyst

University of Massachusetts Boston

Jan 2022 - Dec 2023 (1 year 11 months)

Built PySpark pipelines processing 500GB+ daily to enable near real-time analytics and optimized SQL queries to improve dashboard response time by 40% for 200+ stakeholders; implemented real-time anomaly detection with Kafka and Spark Streaming.

Pyspark PostgreSQL Kafka Power BI Azure Synapse AWS EC2 Lambda Redshift SQL

Associate Data Analyst

TCS

Aug 2020 - Dec 2021 (1 year 4 months)

Analyzed 8M+ customer support logs to reduce ticket resolution time by 25%, built Looker dashboards and dbt models for SLA monitoring, and automated Kafka-driven alerts to cut response lag to high-severity events by 40%.

Python SQL Looker DBT Kafka Geopandas Networkx AWS Lambda

Education

Degrees, certifications, and relevant coursework

University of Massachusetts Boston

Master of Science, Computer Science

2022 - 2023

Activities and societies: Worked on time series forecasting, real-time anomaly detection, dashboard optimization, and automated ML pipelines using Airflow and SageMaker.

Completed a Master of Science in Computer Science focused on data science and scalable ML pipelines, including time series forecasting and real-time analytics.