Lokesh Karanam

About Me

Hello! I'm Lokesh Karanam, a Software Engineer with 5 years of experience specializing in ML model deployment, MLOps, and big data technologies in cloud environments. I'm proficient in tools and frameworks like TensorFlow, PyTorch, Hadoop, Spark, and NoSQL databases, with expertise in designing scalable ETL pipelines and data workflows on AWS and Azure.

I'm skilled in collaborating with cross-functional teams to deploy end-to-end machine learning solutions and optimize data-driven systems. My experience spans from developing Spark applications for processing 50TB of S3 data at RR Donnelley to building serverless architectures at Amazon Web Services for high-velocity real-time data processing.

I'm passionate about leveraging cloud technologies and staying updated on advancements in ML and big data. I hold a Master's in Computer Science from the University of Missouri-Columbia with a 3.9 GPA and am a Databricks Certified Generative AI Engineer Associate.

Skills & Technologies

Programming Languages

Python, Java, C++, SQL, PHP, JavaScript

Data & Cloud Platforms

Snowflake, Databricks, AWS, Azure, MySQL, MongoDB

ML & AI Technologies

PyTorch, TensorFlow, Scikit-Learn, LangChain, Generative AI

Big Data & Processing

Apache Spark, PySpark, Hadoop, Snowpark, ETL Pipelines

Web Development

React, Angular, HTML/CSS, RESTful APIs, Bootstrap

Tools & Frameworks

Git, Docker, Jupyter, VS Code, MATLAB, TestNG

Professional Experience

May 2023 - Present

Staff Software Engineer

RR Donnelley · Austin, TX

Developed Spark application to parse and anonymize 50TB of S3 data, removing PII based on customer deletion requests
Led Snowflake implementation across multiple teams, improving data management and achieving cost savings
Reduced SageMaker infrastructure expenses by 40% through performance optimization and code refactoring
Designed serverless architecture for LLM API usage tracking using SQS, Lambda, and Snowflake
Implemented S3 lifecycle configurations, reducing storage costs by $120K annually

Jul 2022 - Apr 2023

Software Development Engineer

Amazon Web Services · Seattle, WA

Designed serverless application using Lambda, Kinesis, SQS, and SNS for processing 4k records/sec real-time data
Served as on-call engineer ensuring service availability and incident response
Implemented Service Level Objectives (SLOs) and Service Level Agreements (SLAs)
Led post-incident reviews and root cause analyses for continuous improvement

Jan 2021 - Jul 2022

Data Scientist | Teaching Assistant

MU Institute for Data Science and Informatics

Predicted Acute Kidney Injury using novel Residual Time-Gated LSTM, improving accuracy by 7%
Developed Ensembled SVM model with 6% accuracy improvement
Built scalable ETL pipelines for clinical and neighborhood datasets
Assisted in course delivery for Data Mining, Database Analytics, and Network Analytics

Dec 2018 - Dec 2020

Technical Analyst

Axtria Ingenious Insights · Noida, India

Automated testing workflow, reducing manual effort by 60 hours/month
Reduced transition efforts by 50% through standardized documentation processes
Developed test suites using Java, Selenium, and TestNG frameworks
Provided technical support and troubleshooting for Java-based applications

Featured Projects

Data Expert Capstone

A comprehensive data engineering capstone project demonstrating end-to-end data pipeline development, analytics, and visualization capabilities.

Python Apache Spark SQL Data Analytics

View Code

TabMate

A browser extension or web application designed to enhance productivity and tab management, providing users with better organization and workflow optimization.

JavaScript HTML/CSS Browser APIs Web Extension

View Code

Education & Certifications

Master's in Computer Science

University of Missouri - Columbia