Benjamin HughesSr.

Led architecture and development of secure, high-performance Python microservices and APIs for enterprise financial platforms using GenAI and agentic workflows. Built and optimized RAG pipelines indexing 7M+ documents, developed LLM-based chatbots and summarization services deployed to production for 50K+ daily users, and implemented ML services for fraud/anomaly detection and predictive risk scoring exposed via REST APIs. Delivered cloud-native deployments across AWS/GCP/Azure using Docker/Kubernetes and established CI/CD automation and testing practices; also mentored engineers and defined reliability, security, and maintainability best practices.

Led architecture and delivery of secure, scalable cloud-native Python microservices and APIs for enterprise financial platforms. Built GenAI-powered internal productivity tools and agentic AI workflows, processing 1M+ autonomous AI workflows per month across AWS/Azure/GCP. Developed RAG pipelines indexing 7M+ documents with embedding tuning and vector search optimizations to improve retrieval quality by 35%. Shipped LLM-based chatbots and summarization services deployed to production for 50K+ daily users with sub-200ms average response times. Implemented ML services for fraud/anomaly detection and predictive risk scoring exposed via REST APIs, and deployed models using AWS SageMaker with end-to-end MLOps. Improved reliability, observability, and delivery by introducing CI/CD and test automation (coverage 62%→87%) and reducing production defects by 35%.

Built high-performance cloud-native Python microservices and APIs for enterprise financial platforms using GenAI and agentic workflows. Led architecture and performance/observability work across AWS/GCP, including secure authentication/authorization, async processing, database tuning, and CI/CD automation. Delivered production GenAI capabilities such as agentic internal productivity workflows processing 1M+ autonomous workflows monthly, RAG pipelines indexing 7M+ documents, and LLM-based chatbots/summarization serving 50K+ daily users with low latency. Developed ML services for fraud detection, anomaly detection, and predictive risk scoring exposed via REST APIs, and implemented MLOps workflows on AWS SageMaker. Mentored engineers, defined best practices for reliability/security/maintainability, and produced technical documentation and runbooks.