Work
Microsoft Marketplace: Blue Yonder Inventory Ops Agent
Building production agentic capabilities for Blue Yonder's GenAI Pods team across cognitive manufacturing and inventory operations, including the marketplace-listed Inventory Ops Agent for AI-assisted replenishment, forecasting, and multi-location inventory optimization.
Shipping agentic workflows that surface supply-demand mismatches, recommend corrective actions such as alternate sourcing or demand swaps, and turn operational inventory data into production decisions.
Implementing LangGraph orchestration, FastAPI services, Azure OpenAI deployments, tool-calling, MCP integrations, guardrails, and Langfuse eval gates for production workloads.
Delivered agentic services to enterprise manufacturing customers on Azure AI Foundry, contributing to $200K+ paid engagements.
Designed and implemented 30+ CAISO data feed integrations (real-time pricing, grid telemetry, settlement data) into an ingest pipeline processing 5M+ daily transactions for California's wholesale energy market.
Built zero-downtime data synchronization aligned to CAISO's publication cadence, maintaining 99.99% uptime.
Reduced settlement processing from hours to minutes (~95%) by restructuring the database schema, optimizing bulk ingest, and parallelizing compute.
Vast Vertex Media (AI SaaS)
Built AI SaaS platform transforming research papers into interactive podcasts using LLM orchestration (OpenAI, Claude, Groq), ElevenLabs TTS, and custom prompt templating system with 50+ engineered prompts.
Secured meetings with Springer Nature and Wiley to pitch AI-powered academic content transformation, demonstrating product-market fit with major publishing industry leaders.
Developed full-stack platform with FastAPI backend, prompt library architecture, and PDF parsing pipeline that automated complex academic content into engaging audio experiences.
University of Oklahoma – Gallogly College of Engineering
Built biomedical AI data platform processing 1TB+ drug and protein data using S3 storage and entity extraction pipelines that structured DrugBank, FDA, and ChEMBL datasets into searchable noSQL databases.
Processed 1M+ PubMed research papers with NLP pipelines for cancer research, enabling discovery of hidden drug-protein interactions through AI-powered pattern recognition and interactive dashboards.
Achieved successful acquisition by Xyant Services after presenting AI platform capabilities to Johnson & Johnson and NIH stakeholders, contributing to NSF grant development.