profile-pic

Marthala Pavan Kumar Reddy

Innovative Senior Machine Learning Engineer with over 6 years of experience in developing and deploying scalable AI/ML solutions on cloud platforms. Proven expertise in leveraging cutting-edge technologies to drive impactful projects from conception to production, with a focus on optimizing models for superior performance and scalability in cloud environments.
  • Role

    Sr. ML Engineer

  • Years of Experience

    8.58 years

Skillsets

  • MLOps - 3 Years
  • Python - 6 Years

Professional Summary

8.58Years
  • Jan, 2025 - Present1 yr 4 months

    Associate Architect Machine Learning

    Quantiphi
  • Nov, 2021 - Mar, 20253 yr 4 months

    Senior Machine Learning Engineer

    Quantiphi
  • Jan, 2021 - Oct, 2021 9 months

    Data Scientist

    Way2News
  • Oct, 2017 - Jan, 20213 yr 3 months

    Assistant System Engineer

    Tata Consultancy Services

Work History

8.58Years

Associate Architect Machine Learning

Quantiphi
Jan, 2025 - Present1 yr 4 months

Senior Machine Learning Engineer

Quantiphi
Nov, 2021 - Mar, 20253 yr 4 months
    Architected and implemented cloud-based ML solutions, including product recommendation systems and synthetic data generation using LLMs, achieving 70% precision and 30% recall in classification tasks. Developed an end-to-end video summarization pipeline using AWS Bedrock, reducing full-length sports content to 20-minute highlights with 10-minute processing time. Designed and deployed a code conversion pipeline (ODI to PySpark) using AWS Bedrock, achieving over 95% conversion accuracy. Collaborated with cross-functional teams to align ML solutions with business objectives, utilizing AWS services for scalable and cost-effective architectures.

Data Scientist

Way2News
Jan, 2021 - Oct, 2021 9 months
    Developed Text-to-Speech models for vernacular Indian languages and English, improving content accessibility. Implemented object detection applications using YOLOv5, enhancing visual content analysis capabilities. Created similarity search algorithms and content moderation bots, reducing manual workload by 95%.

Assistant System Engineer

Tata Consultancy Services
Oct, 2017 - Jan, 20213 yr 3 months
    Implemented a fraud detection system using Linear Regression with SMOTE sampling, improving accuracy in identifying fraudulent transactions. Developed automation frameworks using Shell Scripting and Python, streamlining data processing workflows.

Major Projects

7Projects

AWS Bedrock-Powered Code Conversion and Video Summarization

    Leveraging AWS Bedrock, designed and implemented an innovative code conversion pipeline that transforms ODI packages into equivalent PySpark code with over 95% accuracy. Additionally, developed an end-to-end video summarization system for sports content, utilizing AWS services to capture key moments from full-length videos. This system efficiently creates highlight versions under 20 minutes in duration, with the entire pipeline conversion process completed in less than 10 minutes. The solution optimizes cloud resources, ensuring both processing efficiency and cost-effectiveness, while demonstrating the ability to handle large volumes of video content at scale.

Product Recommendation using MLops and AWS

    Worked on the development of tailored product recommendation systems for a Retail client, excelling in tasks such as suggesting new items and classifying reorder likelihood across 30 sites with a 20M-record datasets for most of the sites. Leveraged WALS for recommendations, AutoML for classification, and seamlessly integrated MLops for efficient deployment with precision 70% and recall 30%(for classification). Automated end-to-end processes using Airflow DAGs.

Synthetic Tabular Data generation using LangChain and Amazon Bedrock

    Designed and implemented a solution for applications where using production data for testing poses security concerns. Specifically, focused on an LLM-based application that generates synthetic data for Tabular data mirroring the characteristics of the original dataset. By utilizing a few samples of authentic data, the application produces synthetic data with similar traits using LangChain and Amazon Bedrock Claude V2 API. Additionally, established a validation pipeline incorporating exploratory data analysis (EDA) and statistical analysis to ensure the generated data faithfully replicates all characteristics of the original dataset.

Weather Voice Assistant

    Developed a Weather Voice Assistant utilizing AWS services, including Lambda, Comprehend, Lex V2, and Redshift DB. Proficiently managed 10 diverse weather intents, ensuring rapid responses within 300 ms and achieving an Automatic Speech Recognition (ASR) accuracy of 93 %.

Document Parsing application

    Created a Document Parsing application utilizing LayoutLM V4 for extracting necessary fields and signatures from 25 different document types. Employed ResNet50 for checkbox detection, and Detectron for stamp identification, integrated seamlessly with AWS services (Lambda, DynamoDB, SNS, S3). Achieved successful deployment of containerized models, enabling user-friendly interfaces upon image submission with the accuracy of 91 %.

Breaking News detection application

    Implemented an efficient system for object detection and text extraction in real-time YouTube live news channels, enabling rapid coverage of breaking news ahead of competitors. Utilized YOLOv5 model for object detection and OCR for text extraction, achieving a commendable accuracy rate of 89 %. Deployed and optimized the models for seamless and effective integration.

Customized Dashboard for the loan analysis

    Developed and deployed a customized loan analysis dashboard with an integrated data pipeline, leveraging open-source SBA datasets and client-specific data sources. This comprehensive solution enables clients to compare multiple banks and analyze custom characteristics, facilitating informed investment decisions and maximizing profitability. The dashboard's user-friendly interface and powerful analytics capabilities provide clients with real-time insights, reducing decision-making time by up to 40%. Additionally, the system's ability to incorporate diverse data sources has improved the accuracy of loan risk assessments by 25%, leading to a 15% increase in successful loan applications for clients. This tailored solution not only streamlines the loan analysis process but also empowers clients to identify optimal investment opportunities, resulting in an average 20% boost in their investment returns.

Education

  • B.Tech - ECE

    GVP College of Engineering (2017)

Certifications

  • Mlops—machine learning operations specialization : university of dukes - march 2024

  • Applied machine learning in python : university of michigan - august 2020

  • Data science course : codecademy may 2021