Zakary Heppler

Architected and deployed production-grade RAG pipelines and multi-agent orchestration frameworks, reducing hallucination risk and improving semantic retrieval accuracy for enterprise AI services. Built Python and C#/.NET backend services, deployed on Azure Kubernetes Service with CI/CD and telemetry to optimize cost and reliability.

Designed backend control-plane systems and reusable RAG integration layers for lifecycle management of LLM services, enabling secure, autoscaled Kubernetes deployments and Infrastructure-as-Code for Azure environments. Implemented CI/CD gates and telemetry for evaluation and production rollouts.

Developed AI-enhanced backend microservices and hybrid RAG retrieval systems for fintech and healthcare, deploying inference endpoints on AWS and improving reliability via optimized indexing, caching, and logging. Led incident response and translated stakeholder requirements into production AI services.

Built scalable RESTful and GraphQL APIs for recommendation and personalization engines, integrated MLflow for experiment tracking, and implemented caching and CI/CD pipelines to reduce inference latency and streamline model promotion.

Developed backend AI platforms integrating NLP and computer vision models, containerized services for production on AWS, and built orchestration and monitoring systems to support distributed inference and dataset annotation workflows.

Activities and societies: Capstone project on scalable distributed backend systems; collaborative engineering projects, version control and peer review workflows.

Completed a Bachelor’s Degree in Computer Science with coursework in data structures, algorithms, distributed systems, artificial intelligence, and databases; capstone focused on scalable distributed backend systems.