Dharmateja Chelamalasetty Email & Phone Number

Irving, Tx, Us

Dallas, Tx, Us

Leading the design, implementation, and management of advanced Data + AI and Generative AI solutions, ensuring alignment with business goals. Oversee cross-functional teams, manage project timelines, and drive product innovation and efficiency• Copart Genie:Spear heading the Gen AI code assistant which generates/explains the code to improve the developer’s productivity.Integrating Applications to leverage/boost the performance with routing mechanism to leverage open & closed weight source models.Integrating with BI platform to generate text to sql for Ad-hoc Analysis.• Real-time Anomaly Detection:Currently leading a team to conduct real-time data analysis for anomaly detection, such as identifying reductions in the number of assignments.• AI-Powered Image Enhancement:Led the development of image services to remove backgrounds and enhance images, improving user experience by 20%.Led the automation of detecting poor quality in images, reducing turnover time from 24 hours to a few seconds and eliminating the need for 97% of reimaging requests.Led the implementation of data extraction from images, capturing VIN numbers, odometer readings, and engine fault codes, resulting in a 20% improvement in data quality.• Smart Dispatch :Led in Implementing a ranking algorithm to recommend vendors for specific vehicles and vice versa, based on cost and historical trip data, resulting in $1 savings per CPC and a 50% reduction in trip/work request assignment time.• Copart Data Platform:Migrated MemSQL to Google BigQuery, providing users with a unified source of truth for both transactional and analytical purposes.

Dallas, Tx, Us

• Retrained Deep Neural Network image recognition models for vehicle damage scoring on four corners using CNN and transfer learning, achieving an AUC of 0.89, achieving 20% improvement.• Implemented augmentation, Hyper opt, callbacks, class weights, and gradient clipping techniques to achieve a 30% reduction in overall model loss. Optimized model performance through quantization and parallelization techniques, achieving a 20% runtime improvement.• Enhanced OTL classification model using GBM by integrating scores from Deep NN Model, resulting a 6% AUC improvement.• Implemented new Pro-quote model for the DE team, utilizing GBM to anticipate the price quotation (Estimated Sale Price in Auction) for a Lot, and able to achieve Mean cross-validation score to 88%, with RMSE 1232.25 through data preprocessing, feature engineering, and hyper-parameter tuning which resulted in 2% improvement of existing US PQ Model.• Created Tableau dashboards to offer insights into PQ and Damage score models.

Richardson, Texas, Us

• Teaching Assistant for MIS 6326: Data Management, guided over 190 students in Data Management using SQL• Supported the professor with class experiment setup, examination proctoring, and assignment grading

Bengaluru, Karnataka, In

As ML Specialist performed complex research and analysis for launching/Enhancing ML models for Ads & Video Recommendation Systems from HQ to Asia Pacific Region• Analyzed models to predict pCTR for different Ad Types: Banner, Native Ads, Interstitial Ads, IGA ads, Reward Video.• Developed models for different Video types: Short Video, Similar Video, Long Video, TV• Models Used: FLTR, LR, Decision Tree Bucketing, SVD, CF, Cosine Similarity, Rule Based, Popularity Based.Key achievements:• Implemented successfully and launched Ads Recommendation Systems in Asia Pacific region for all ad types and provided ads recommendation for 4 million users per day.As Data Analyst Performed complex research and analysis for migrating traditional reporting platform to self-analytics platform & Provided insights by building Dashboards for different APP business of honor mobile line .• Data Extracted and transformed into multiple layers from ODS, DIM, DW and ADS Layers.• Built Pipelines & created tasks using BI tools & TCC to transform the data into different layers.• Identified & analyzed and interpret trends or patterns in complex data sets and performed RCA for data quality concerns.Key achievements:• Successfully launched self-analytics platform and migrated close to 400+ reports.

Bengaluru, Karnataka, In

As Solution architect for Online Charging System (Prepaid billing System),Convergent Billing System (Post Paid Billing System) ,Wireless Intelligent network and Fixed Intelligent networks for Telecom Service Providers across Europe, Africa, Asia, South America Regions.• Defined and documented business requirements in document (BRD) containing details such High-level introduction, Scope, Business requirements (including As-IS and To-Be system), Process flow diagram, Use Cases.Key achievements:• Defined and provided BRD/FRS for about more than 100 customized versions and successfully involved in 50 migration projects during this tenure.

Master Of Science In Business Analytics, Data Science

Pgp - Machine Learning, Information Technology

Bachelors, Electrical, Electronics And Communications Engineering