Reza Hashemi
Oceanside,CA
Summary
Accomplished Data Scientist and Lead Scientist at Fair Isaac Corporation with expertise in machine learning, deep learning, and big data analytics. Proven track record of deploying production ML systems processing 800M+ records with 120x performance improvements using distributed computing. Expert in statistical modeling, feature engineering, and building interpretable models for regulated industries. Strong background in cross-functional collaboration, delivering data-driven solutions that drive business impact.
Overview
9
9
years of professional experience
Work History
Lead Data Scientist / Lead Scientist
Fair Isaac Corporation (FICO)
08.2022 - Current
- Designed and deployed scalable fraud detection models using PySpark on AWS SageMaker, analyzing 800 million records in ~40 minutes—achieving 120x performance improvement over baseline
- Built end-to-end ML pipelines from data ingestion, feature engineering, model training, to deployment and monitoring in production environments
- Developed interpretable neural networks with PyTorch for non-linear feature extraction, enhancing model explainability to meet regulatory compliance requirements
- Conducted hyperparameter optimization using Optuna and Ray Tune, improving model accuracy by 15% and reducing false positive rates
- Performed advanced feature engineering and statistical analysis on large-scale financial datasets to identify predictive patterns and improve model performance
- Collaborated with product managers, engineers, and compliance teams to deliver ML solutions meeting strict business and regulatory requirements
- Applied model explainability techniques (SHAP, LIME) to interpret predictions and provide actionable insights to stakeholders
- Mentored students for FICO Educational Challenge on large language models (LLMs), providing guidance on Qwen and BERT model implementations and optimization
- Architected and deployed Kubernetes cluster on AWS EC2 nodes for containerized ML model deployment, enabling scalable and resilient production infrastructure
- Implemented real-time data streaming pipelines using Apache Kafka and Apache Pulsar for high-throughput messaging and event-driven architectures, processing millions of transactions daily
- Implemented efficient data serialization using protocol buffers in Java for production systems
Senior Data Scientist / Senior Research Scientist
Intelligent Automation Inc.
06.2019 - 08.2022
- Built predictive models using ensemble methods (Random Forest, XGBoost, LightGBM) to forecast mobile traffic patterns in LTE networks with 92% accuracy
- Conducted extensive exploratory data analysis and feature engineering on large-scale telecommunications datasets to extract meaningful insights
- Applied advanced signal processing and statistical methods for pattern recognition and anomaly detection in RF data
- Developed radar signal processing algorithms for detecting naval objects and modeling sea surface characteristics, improving target detection accuracy in maritime environments
- Created interactive data visualizations and dashboards using Python (Plotly, Matplotlib, Seaborn) for communicating complex analytical findings to stakeholders
- Performed statistical hypothesis testing and A/B testing for validating model performance and system improvements
- Developed geospatial analytics solutions for telecommunications network optimization
- Led technical contributions to two successful SBIR proposals for the Department of Defense, securing $1.5M in research funding through data-driven insights and methodologies
Senior Data Scientist / Senior Engineer
Automated Precision Inc.
08.2016 - 06.2019
- Developed computer vision models using CNNs for automated defect detection and classification on industrial parts, achieving 95% classification accuracy
- Built data preprocessing and augmentation pipelines for cleaning, normalizing, and preparing large image datasets for deep learning models
- Implemented GPU-accelerated computing using CUDA for processing point cloud data from LiDAR systems, reducing processing time by 80%
- Applied dimensionality reduction techniques (PCA, t-SNE) for feature extraction, analysis, and visualization of high-dimensional data
- Designed real-time object detection algorithms for quality control systems in manufacturing environments
- Conducted A/B testing and statistical validation of ML models in production to ensure reliability and performance
- Collaborated with engineering teams to integrate data science solutions into operational systems
Education
PhD - Electrical Engineering
University of Arkansas
FayettevilleSkills
- Machine Learning & AI
- Statistical Modeling
- Deep Learning
- Data Mining
- Big Data Analytics
- Predictive Modeling
- Feature Engineering
- Model Optimization
- Python (Pandas, NumPy)
- PySpark & Distributed Computing
- SQL & Database Management
- AWS (SageMaker, EC2, S3)
- PyTorch & TensorFlow
- Scikit-learn & XGBoost
- Data Visualization
- Matplotlib, Seaborn, Plotly
- Time-Series Analysis
- A/B Testing
- Hyperparameter Tuning
- Optuna, Ray Tune, Bayesian Opt
- Model Explainability
- Kubernetes Cluster
- Kafka & Pulsar
- Ensemble Methods
- Neural Networks (CNNs, DNNs)
- Regression & Classification
- Clustering & Dimensionality Reduction
- Computer Vision
- Image Processing
- Signal Processing
- Natural Language Processing
- ETL & Data Pipelines
- Cloud Computing
- Git Version Control
- Cross-functional Collaboration
- Statistical Hypothesis Testing
- Exploratory Data Analysis
- CUDA & GPU Computing
- C Programming
- RF & Electromagnetics
- Microwave Imaging
Awards & Recognition
ASEE/NSF Small Business Postdoctoral Research Diversity Fellowship, Honorable Mention Paper, IEEE International Symposium on Antennas and Propagation, John A. White Faculty-Student Collaboration Award, NSF Award, San Diego Supercomputer Center, Listed in Marquis Who's Who in America and Who's Who in Science and Engineering
Selected Publications
- "Non-invasive detection of optical changes elicited by seizure activity using time-series analysis," Journal of Neuroscience Methods, 227, 2014, 18-28
- "Noninvasive evaluation of nuclear morphometry in breast lesions using multispectral diffuse optical tomography," PLOS ONE, 7, 9, 2012, e45714
- "High performance computing for the level-set reconstruction algorithm," Journal of Parallel and Distributed Computing, 70, 6, 2010, 671-679
- "Shape Reconstruction Using the Level Set Method for Microwave Applications," IEEE Antennas and Wireless Propagation Letters, 7, 2008, 92-96
- Full list of publications: Google Scholar Profile
Timeline
Lead Data Scientist / Lead Scientist
Fair Isaac Corporation (FICO)
08.2022 - Current
Senior Data Scientist / Senior Research Scientist
Intelligent Automation Inc.
06.2019 - 08.2022
Senior Data Scientist / Senior Engineer
Automated Precision Inc.
08.2016 - 06.2019
PhD - Electrical Engineering
University of Arkansas