Data Engineering Machine Learning

CHARITH PURUSHOTHAM

Email: *****************@*****.***; Phone: +1-720-***-****; Portfolio: link; LinkedIn: Charith Purushotham; CO, USA ACADEMIC QUALIFICATION

University of Colorado Boulder, USA, Master of Science (Research), Computer Science CGPA: 3.82/4.00 August 2024 - May 2026 Dayananda Sagar College of Engineering, India, Bachelor of Engineering, Computer Science CGPA: 9.68/10.00 August 2018 - June 2022 TECHNICAL SKILLS

Programming and Development: C, Java, Python, Flask, React.js, Node.js, MySQL, MongoDB, Git, GitHub Cloud and Operating Systems: Microsoft Azure, AWS, Windows, Linux Data and Machine Learning: Excel, Tableau, Databricks, TensorFlow, Scikit-learn, OpenCV, Pytorch, RAG, Caret, ggplot2, LlamaIndex Project Management and Other Technical Skills: Azure boards, OOP, System Design, Docker, Kafka, Snowflake, Bot Framework PROFESSIONAL EXPERIENCE

Phamax, Bengaluru, Associate Software Development Engineer September 2022 - July 2024 Ariya Product

● Collaborated on the system architecture for the digital assistant "Ariya," now a Microsoft-certified SaaS on the MS Teams store. Contributed to design, boosting subscriptions by 5% and client engagement by 7%, demonstrated by a higher client demo rate.

● Implemented GPT features with OpenAI and Azure, enhancing data summarization and insights. Dockerized the solution, resulting in a 20- 25% resource efficiency increase and reducing deployment time by 50% (from 15 minutes to 7 minutes)

● Managed user and group administration on Azure, deployed Docker containers for efficient application deployment, and implemented automated logging and monitoring systems for improved user experience. Medinfo chatbot Project

● Collaborated on the content processing system architecture, which handles data from the client's IRMS to the SFTP data container.

● Implemented a custom Q&A system for user queries and an application logging system to record conversation transcripts. The logging system increased user engagement with the chatbot by 5% due to regular feedback from monitoring the transcripts. Santen Data Engineering Project

● Led a data engineering project for Santen using Databricks and Azure, halving processing time from 30 to 12-15 minutes and improving data accuracy by implementing checkpoints for data evaluation. Implemented a medallion architecture, enhancing Tableau performance by offloading heavy processing to Databricks.

Project Research and Development

• Developed a Retrieval-Augmented Generation (RAG) pipeline using Bedrock for pharmaceutical document summarization, leveraging S3, vector DBs, and LLM orchestration and explored Amazon SageMaker to deploy a classification model for adverse drug reaction (ADR) detection using clinical notes and prescription data. Tech-stack: Node, React, Microsoft Bot Framework, Flask, Microsoft Azure, Docker, Databricks, AWS, Bedrock, SageMaker, S3 Fittlyf, Bengaluru, Data Science Intern April 2022 - August 2022

● Developed a Multi-Arm Bandit framework for an in-house reporting tool, optimizing A/B test traffic and reducing turnaround time by 40%. Implemented Group Sequential Sampling to adjust significance thresholds, accelerating decision-making and cutting turnaround time by 46%. Automated logging of metrics and report generation enhanced overall efficiency.

● Developed an MVP AI-based solution in the computer vision domain, using human pose estimation (Blazepose model) and deep learning, to help physiotherapists monitor and report the status of exercise routines for their patients. Tech-stack: Python, Jupyter Notebook, OpenCV, Flask, Tableau, Excel and Bigquery PROJECTS AND PUBLICATIONS

Human pose estimation in fitness tracking and guidance:

● Developed an AI-based human pose detection tool using BlazePose for real-time exercise monitoring. Built a website with HTML, CSS, Node.js, and JavaScript, integrating exercise metrics and deep learning yoga pose classification. Automated data reporting via email for user engagement and tracking. Research paper: “Spatial Structure-oriented and Angle-based Human Pose Estimation for Pose Classification” in International Journal For Multidisciplinary Research (IJFMR),Volume 5, Issue 6 (November-December 2023)- link Contour tracking and detection of heart chamber:

● Developed methods for detecting blood chambers in echo video frames at a hackathon, focusing on the left ventricle. Used Python, OpenCV, Pydicom, and Deep Gaze. This project highlighted AI's role in improving cardiac healthcare and explored advanced segmentation techniques like U-Net. Research paper: “Contour tracking and detection of heart chambers in an echocardiogram video sequence using U-Net” in International Research Journal of Modernization in Engineering Technology and Science (IRJMETS), Volume:05, Issue:07, July-2023- link Full-Stack E-Commerce application:

● Developed a scalable, responsive web application using React.js, Node.js, Express.js, and MongoDB, implementing JWT authentication, RESTful APIs, and state management with Redux. Integrated secure payment gateways (Stripe), real-time order tracking, Redis for caching, and a dynamic admin dashboard for managing orders, inventory, and user interactions- link LinkedIn Job Market Analysis and Recommendation System:

● Developed a job market forecasting tool using LinkedIn data, applying ML models (ARIMA, clustering) for trend analysis, skill demand, and remote work insights. Implemented probabilistic clustering based on common job description keywords. Built a data cube for interactive analytics, uncovering industry salary trends, job visibility impact, and demand in tech and healthcare- link ACHIEVEMENTS

● “Human pose estimation in fitness tracking and guidance” project was awarded “Best Project of the Year” in the Computer Science category during the state-level seminar and exhibition held at VTU, Belagavi, August 2022, supported by KSCST.

● “RePosture AI” project was awarded “3rd place in the T9-MediHack 2025 (24hr Hackathon) in the Artificial Intelligence track” – RePosture AI is an AI-driven posture correction tool that leverages computer vision, machine learning, and real-time feedback for ergonomic wellness- link

● “AWS Jam Hackathon” – University of Colorado Boulder: Placed 7th, solving 9/13 security challenges using AWS services like Lambda, CloudTrail, DynamoDB, S3, VPC, IAM, and SageMaker, gaining hands-on experience in cloud security and threat mitigation. EXTRACURRICULAR

● Co-Founder, Data Science and AI-ML Student Club, Layers (Dec 2021 - Present): Lead Layers Club to promote knowledge sharing, networking, and skill development in Data Science and AI-ML.

● Technical/Data Consultant, Data Buffs (Jan 2025 - Present): Working on data extraction, backend development, and statistical analysis for data-driven insights.

Contact this candidate