Manish M.

About Manish M.

I am a Data Scientist experienced in handling big data with MySQL and Pyspark. My research and academic projects include objection detection and segmentation, time series prediction, NLU, 3D reconstruction. I have experience in building ETL pipelines and MLOps Experience in collecting, analyzing and storing data in warehouses, databases and data lakehouse Received, cleaned, and prepared data from client using Python and SQL.GitHub: https://github.com/Manish22332

Experience

1. Machine Learning Engineer

   卡特彼勒

   Mar 2023 — Present

   Developed a transformer model in Pytorch for autonomous train control, improving fuel efficiency by 5% as compared to deployedmodel resulting in more than 150 gallons of fuel savings per tripAutomated validation of real-time data collected from autonomous vehicles, ensuring accuracy and reliability before model trainingand deployment and thereby reducing time by 80% for validation of dataEngineered an automated data transfer pipeline from autonomous vehicles to Amazon S3 with OpenSearch Indexes, ensuring secureand efficient data management, with built-in validation to confirm data integrityStreamlined the end-to-end data processing workflow, reducing manual intervention and improving the efficiency of model trainingand validation processes thereby reducing storage cost by 10%Collaborated with cross-functional teams to integrate a DQN models in Rust with vehicle control systems, resulting in measurableimprovements in driving efficiency and performance Integrated data version control(dvc) into the model development process, increasing the reproducibility of the model by 10 folds

Education

• Carnegie Mellon University

  Master of Science - MS

  2021 — 2021

• University of Mumbai

  Bachelor of Engineering, Civil Engineering

  2015 — 2019