Jeffrey Conradi
Details
Skills
Data Science, Machine Learning, Artificial Intelligence, Applied AI, AI Engineering, ML Engineering, MLOps, Computer Vision, Natural Language Processing, NLP, Supervised Learning, Unsupervised Learning, Classification, Regression, Ranking Models, Recommendation Systems, Time Series Forecasting, Anomaly Detection, Object Detection, Image Segmentation, Document Classification, Sentiment Analysis, Clustering, Feature Engineering, Transfer Learning, Fine-Tuning, Ensemble Learning, Class Weighting, Data Augmentation, Hyperparameter Optimization, Model Evaluation, Model Validation, Precision, Recall, F1 Score, Mean Average Precision, Confusion Matrices, Calibration, Threshold Optimization, Error Analysis, Explainable AI, SHAP, Bias Analysis, Data Drift Detection, Model Monitoring, Model Lifecycle Management, Python, SQL, Java, TypeScript, JavaScript, PHP, Scala, PyTorch, TensorFlow, scikit-learn, XGBoost, LightGBM, StatsModels, YOLO, DETR, ResNet, LangChain, OpenAI APIs, Apache Spark, PySpark, Databricks, Airflow, Pandas, NumPy, Kafka, ETL, Data Pipelines, Data Engineering, Snowflake, Redshift, Cosmos DB, AWS, Azure, Google Cloud, AWS Glue, Amazon S3, SageMaker, GKE, Cloud Run, Pub/Sub, FastAPI, Flask, REST APIs, GraphQL, gRPC, WebSocket, RabbitMQ, Microservices, Docker, Kubernetes, Terraform, CloudFormation, GitHub Actions, Azure DevOps, Jenkins, CI/CD, MLflow, Azure ML, CloudWatch, Production Observability, Structured Logging, GPU Monitoring, Inference Optimization, Latency Optimization, Infrastructure Cost Optimization, Model Deployment, Production ML, API Development, Asynchronous Python, Data Annotation, Automated Annotation, Segment Anything Model, SAM, OAuth 2.0, JWT, RBAC, Encryption, Audit Logging, HIPAA, PHI Handling, Technical Requirements, Stakeholder Communication, AI Use-Case Definition, Technical Design, Production Troubleshooting.
About
Jeffrey Conradi is a Senior Data Scientist and AI/ML Engineer with more than 10 years of experience developing production machine learning systems, applied AI solutions, cloud-native platforms, and scalable data workflows. At Hyatt Hotels Corporation, he develops AI solutions for property operations, visual inspection, asset monitoring, occupancy analytics, and operational automation, contributing to a 36% improvement in processing efficiency. His work spans computer vision, classification, object detection, segmentation, anomaly detection, model evaluation, Python-based APIs, Databricks, PySpark, Airflow, and AWS, while his optimization of production AI workloads reduced infrastructure costs by 23%. Previously at Urbint, Jeffrey architected a real-time AI risk detection platform integrating more than 200 CCTV streams, built computer vision and NLP pipelines, and worked with LLM-based recommendation models. At Cisco, he developed NLP recommendation, document classification, clustering, segmentation, and distributed Spark ML solutions. His earlier ML Data Engineering experience included high-volume ETL, feature engineering, real-time inference APIs, microservices, annotation platforms, and e-commerce personalization.