Yashwanth Reddy Boddireddy
Where Data Meets Development
Transforming complex data into intuitive solutions through full-stack development and data science
2+
Years Experience
15+
Projects Completed
10+
Technologies Mastered
My Journey
From Electrical Engineer to full-stack data development, my path has been driven by a passion for solving complex problems with data and code.
Yashwanth Reddy Boddireddy
At the intersection of AI innovation and data science, I transform complex problems into impactful solutions that drive measurable business outcomes.
Software Engineer specializing in AI applications and machine learning, helping organizations leverage data for competitive advantage. With experience at Accenture and Headstarter AI, I focus on developing intelligent systems that enhance user experiences.
I combine technical expertise with business acumen, following a systematic approach: understanding requirements, designing data-driven architectures, and implementing scalable solutions with measurable results.
Master of Science in Data Science, Statistics @ New Jersey Institute of Technology (NJIT), Newark, NJ
Web Resource Data Scientist @ VMware
- Partnered with product and engineering teams to identify and frame 10+ high-impact business problems across SaaS product telemetry and cloud infrastructure, leading to a 15% improvement in customer retention via targeted insights
- Designed and automated data pipelines using PySpark and SQL to ingest and process ~3 TB of telemetry and log data daily from VMware's vSphere and NSX platforms, reducing data availability latency from 12 hours to under 2 hours
- Built and deployed machine learning models (e.g., random forest, logistic regression, anomaly detection) to predict VM resource exhaustion and detect anomalous user behavior, increasing proactive alert accuracy by 28%
- Engineered 100+ features from product usage logs, cloud performance metrics, and customer support data, and conducted hyperparameter tuning using MLflow and Optuna to improve F1-score by 22% across models
- Delivered containerized ML inference services (Flask + Docker) deployed via Jenkins and Kubernetes, reducing model deployment cycles from 5 days to under 1 day and enabling real-time scoring for 50K+ daily API calls
- Monitored deployed models for concept drift and performance decay using Grafana and Prometheus dashboards; retrained models monthly using scheduled Airflow workflows, maintaining <5% prediction error across quarters
- Created interactive dashboards and reports in Tableau and Power BI to visualize model predictions and business KPIs, which were used weekly by senior leadership to guide roadmap and operational decisions
Software Engineering Fellow @ Headstarter AI
- Built 5+ AI apps and APIs using NextJS, OpenAI, Pinecone and Stripe API
- Successfully led 4+ engineering fellows to deliver projects from design to deployment
- Enhanced team productivity through effective leadership and collaboration
Sr. Data Scientist @ Accenture
- Led a cross-functional initiative to design and launch a recommendation engine for personalized content across HBO Max, resulting in a 19% increase in average user session duration and a 12% boost in monthly active users (MAU) within the first quarter of deployment
- Architected and deployed a real-time churn prediction system using ensemble models (LightGBM, XGBoost) on a Spark-based pipeline, enabling targeted retention campaigns that reduced churn by 8.5% YoY in key demographic segments
- Directed the end-to-end experimentation pipeline, including A/B testing frameworks and causal inference techniques (e.g., uplift modeling, propensity scoring), to evaluate content previews and marketing placements across digital platforms — increasing click-through rates by 2%
- Managed large-scale data acquisition and enrichment pipelines using Airflow and AWS Glue to process over 5 TB of daily user interaction logs, integrating data from third-party ad platforms, streaming analytics, and CRM tools for unified audience profiling
- Developed NLP-based models (topic modeling, sentiment analysis) on viewer feedback and closed-caption text to inform editorial decisions and improve trailer targeting, contributing to a 30% lift in trailer-to-watch conversion for new releases
- Collaborated with product, engineering, and data governance teams to define data standards and deploy modular, reusable ML components using Databricks and MLflow, cutting model delivery timelines by 30% across business units
- Mentored a team of 3 junior data scientists and analysts, conducting regular peer code reviews, technical deep dives, and knowledge-sharing sessions to elevate team productivity and ensure reproducibility and scalability in deployed solutions
Technical Proficiency
A comprehensive overview of my technical skills in data science, engineering, MLOps, and development technologies.
Core Competencies
Featured Work
A showcase of my projects spanning data visualization, full-stack applications, and data analysis solutions.
Get In Touch
Have a project in mind or interested in working together? I'd love to hear from you. Let's create something amazing.