Software Engineer Data

VARA PRASAD BANDARI

513-***-**** *******************@*****.*** LinkedIn

PROFESSIONAL SUMMARY

Data Engineer with 3+ years of experience building scalable ETL pipelines and implementing CDC for data lake hydration. Expertise in Apache Spark for real-time and batch processing, integrating for analytics, and optimizing performance on cloud platforms. Demonstrated ability to transform raw data into queryable insights using Python, Java, and big data technologies while ensuring efficient data orchestration and delivery. PROFESSIONAL WORK EXPERIENCE

Pfizer Inc. Jul 2024 - Present

Senior AI/ML Software Engineer New York, NY

• Delivered a 25% reduction in clinical trial timelines and $2M annual savings by developing CNN-based biomarker detection models and automated genomic pipelines under FDA-compliant MLOps workflows.

• Enhanced imaging accuracy to 94% by implementing computer vision algorithms with transfer learning, enabling early biomarker detection and improved patient safety monitoring.

• Engineered predictive analytics models using ensemble methods and gradient boosting to forecast patient outcomes and reduce adverse events in clinical trial pipelines.

• Optimized model inference by 40% through quantization, compression, and distributed computing, enabling large-scale deployment on Databricks, Apache Spark, and AWS SageMaker.

• Developed real-time anomaly detection systems leveraging Spark Streaming and AWS SageMaker to monitor clinical trial data in compliance with GxP and FDA standards.

• Integrated MLflow and LangGraph for automated retraining, experiment tracking, and modular workflows, reinforcing end-to-end AI governance. Flipkart Internet Pvt Ltd May 2022 - Nov 2023

ML Software Engineer Bangalore, India

• Boosted click-through rate by 35% and conversions by 20% by deploying LSTM- and BERT-powered recommendation engines across a 400M+ user base.

• Enhanced inventory efficiency by 18% using demand forecasting models built with ARIMA, LSTM, and Prophet to optimize distribution across 80+ warehouses.

• Improved product search relevance by implementing NLP models for categorization, search ranking, and multilingual product classification.

• Reduced fraudulent activity by 60% and saved $5M annually by designing anomaly detection frameworks employing graph neural networks and isolation forests.

• Devised large-scale A/B testing pipelines to assess campaign effectiveness and refine marketing strategies for mobile and web platforms.

• Engineered real-time ETL pipelines handling 10TB+ daily transactions by leveraging Apache Kafka, Apache Spark, and Airflow to enable scalable, low-latency analytics.

Zerodha Broking Ltd May 2021 - Apr 2022

Data Science Engineer Bangalore, India

• Developed automated trading bots using Monte Carlo simulations and GARCH volatility models, reducing execution latency and enhancing portfolio profitability.

• Constructed real-time surveillance systems with anomaly detection to flag suspicious trades, ensuring SEBI regulatory compliance and mitigating risks.

• Formulated customer segmentation models using clustering and RFM analysis, driving personalized upselling strategies for premium trading services.

• Reduced portfolio risk exposure by establishing VaR-based risk management frameworks and volatility forecasting models for proactive mitigation.

• Enhanced trading intelligence through Tableau dashboards and Python reporting tools, boosting transparency for executives and regulatory reporting.

• Architected low-latency streaming systems using Apache Kafka and Redis to manage market data feeds, ensuring reliable and scalable trading signal execution.

TECHNICAL SKILLS

• Programming Languages: Python, SQL, Java, Scala, C++, R, JavaScript, Bash, Go, MATLAB

• Machine Learning & AI: TensorFlow, PyTorch, Scikit-learn, Keras, XGBoost, LightGBM, OpenCV, NLTK, spaCy, Hugging Face Transformers, MLflow, Kubeflow, AutoML, DSPy, LangGraph, Experiment Tracking

• Deep Learning: CNN, RNN, LSTM, GRU, Transformer, BERT, GPT, Computer Vision, Natural Language Processing, Reinforcement Learning, Generative AI

• Big Data & Cloud: Apache Spark, Kafka, Hadoop, AWS (SageMaker, EC2, S3, Lambda, CloudWatch), GCP (BigQuery, Vertex AI, Cloud Functions), Azure ML, Databricks, Snowflake, Apache Hudi, AWS Deequ, AWS Skillset, Apache Griffin

• MLOps & DevOps: Docker, Kubernetes, Jenkins, Git, CI/CD, Model Versioning, A/B Testing, Monitoring, Logging, Automated Testing, Infrastructure as Code, Azure DevOps, GitLab CI/CD, Model Governance, Apache Airflow

• Data Analysis: Pandas, NumPy, Matplotlib, Seaborn, Plotly, Tableau, Power BI, Excel, Statistical Analysis, Data Visualization, Feature Engineering

• Databases: MySQL, PostgreSQL, MongoDB, Redis, ElasticSearch, Neo4j, Data Warehousing, ETL Pipelines, Data Modeling, Change Data Capture EDUCATION

University of Cincinnati Jan 2024 - May 2025

Master's, Information Technology, AI/ML Specialization

• GPA: 3.96

Sathyabama Institute of Science and Technology India Jun 2019 - May 2023 Bachelor of Technology, Computer Science and Engineering

• GPA: 3.83

Contact this candidate