Chandan Chalumuri
Tempe,AZ
Summary
Results-driven AI/ML Engineer with 4 years of experience designing and implementing scalable machine learning and NLP solutions for financial and technology sectors. Skilled in Python, SQL, TensorFlow, and PyTorch, with expertise in data preparation, model deployment using AWS SageMaker, and developing ETL/ELT pipelines. Solid background in cloud-native application development and data security.
Overview
1
1
Certification
6
6
years of professional experience
Work History
Artificial Intelligence Engineer
Equifax
Tempe, Arizona
01.2025 - Current
- Prepared feature datasets for machine learning workflows, reducing underwriting data preparation time by 30% and enhancing model team readiness.
- Developed Kafka-based streaming ingestion pipelines managing over 1 million events daily, achieving 99.5% reliability and reducing delayed-data incidents by 35%.
- Engineered PySpark and Python ETL/ELT pipelines processing over 15 million credit-risk records daily, reducing data-processing latency by 31%.
- Automated ingestion, transformation, and publishing across 20+ source datasets, decreasing manual preparation effort by 40%.
- Built and optimized over 50 SQL transformations, enhancing data completeness and reporting accuracy by 27% for analytics workflows.
- Supported AWS SageMaker and MLflow deployment governance for over five model releases, enhancing traceability and reducing coordination time by 25%.
- Automated monitoring for 30+ scheduled pipelines, reducing mean time to detect workflow failures by 45%.
- Implemented reconciliation controls and quality checks, uncovering issues related to $4 million in annual transactional exposure.
Data Engineer
Borland Software
Pune, maharashtra
09.2020 - 06.2023
- Developed and maintained over 25 Python, SQL, and Apache Airflow ETL pipelines, enhancing ingestion accuracy by 30%.
- Orchestrated 40+ scheduled Airflow workflows, increasing on-time pipeline completion from 85% to 97% through effective dependency management.
- Created SQL transformations and reporting datasets for 15+ business domains, streamlining ad hoc data requests and reducing turnaround time by 45%.
- Constructed ML-ready datasets for recommendation forecasting and segmentation, reducing data-preparation time by 35%.
- Built random forest recommendation models, achieving a 14% improvement in enterprise-client retention.
- Executed PyTorch neural-network experiments that decreased demand-forecasting deviation by 12%.
- Automated document classification using NLP, enhancing accuracy by 18% and reducing manual review efforts by 30%.
- Containerized 12+ data processing components with Docker, minimizing environment-related deployment issues by 50%.
Education
Master of Science - Information Technology
Arizona State University
Tempe, AZ05-2025
Bachelor of Science - Computer Science
Gandhi Institute of Technology And Management
India04-2023
Skills
- NLP applications
- Model evaluation
- Feature engineering
- Model monitoring
- Python and TensorFlow
- PyTorch and Scikit-learn
- SQL and PySpark
- Apache Spark and Kafka
- Cloud AI services
- Azure storage solutions
- Container orchestration
- Automated deployment
- Data architecture
Certification
- Image Processing with Python
Timeline
Artificial Intelligence Engineer
Equifax
01.2025 - Current
Data Engineer
Borland Software
09.2020 - 06.2023
Master of Science - Information Technology
Arizona State University
Bachelor of Science - Computer Science
Gandhi Institute of Technology And Management