Headline

AI/ML Engineer | AWS · Databricks · GCP | Building Scalable ML & Data Pipelines

About

I build machine learning systems that don’t just work in notebooks—they scale in real-world data environments. Currently at Accenture, I work on migrating enterprise data pipelines from AWS Glue to Databricks using DBT and DBX, making them more scalable and maintainable. Alongside this, I develop supervised machine learning models using cross-validation and hyperparameter tuning, and run training workflows on AWS SageMaker to support production-ready experimentation. My work sits at the intersection of machine learning and data engineering—designing pipelines, improving model performance, and working with large-scale data systems. I’ve built end-to-end ML solutions across different domains, including: A heart disease prediction system (88.16% accuracy, 0.88 ROC-AUC) using AWS SageMaker Criminal network analysis using graph-based disruption strategies Image denoising using CNN-based autoencoders My core strengths include machine learning, cloud-based ML workflows (AWS, Databricks), and building scalable data pipelines. I’m currently looking for opportunities in AI/ML Engineering where I can work on real-world, scalable machine learning systems.

Location

Hyderabad

Work experience

Associate Software Engineer at Accenture in India, Jul 2024 - Present · 1 yr 11 mos, Hyderabad, Telangana, India, Migrated AWS Glue ETL pipelines to Databricks using DBT and DBX, resulting in improved scalability and simplified pipeline maintenance across enterprise workflows. Developed supervised ML models using scikit-learn with cross-validation and hyperparameter tuning, resulting in improved model performance for internal AI-driven use cases. Executed ML training workflows on AWS SageMaker using S3-based datasets, enabling scalable experimentation and faster model iteration cycles. Optimized enterprise data pipelines using webMethods by identifying bottlenecks, resulting in reduced processing inefficiencies and improved workflow reliability.

Machine Learning Intern Trainee at Indian Servers - Software Development Company, Apr 2022 - May 2022 · 2 mos, Vijayawada, Andhra Pradesh, India, Built a convolutional autoencoder using TensorFlow for image denoising, resulting in effective noise reduction and improved image reconstruction quality. Developed preprocessing pipeline with Gaussian noise injection using NumPy, enabling robust model training across multiple noise conditions. Optimized training using MSE loss and tuning techniques, resulting in reduced reconstruction error and improved model stability.

Education

Bachelor of Technology - BTech, Computer Science and Engineering, R.V.R. & J.C. College of Engineering

Minor Degree, Cloud Computing, R.V.R. & J.C. College of Engineering

Public links

github: https://github.com/suhas7842