I build backend systems and AI-driven services for regulated and enterprise environments.
My background is in trading and financial infrastructure, where reliability, validation, and controlled execution are critical. Most of my work involves Python services, event-driven systems, and integrating LLM capabilities into production software.
Recently I've focused on making AI systems deployable in real environments by constraining probabilistic LLM behavior with traditional engineering practices—clear service boundaries, deterministic execution paths, validation, and observable system behavior.
Core expertise
Backend systems engineering • Event-driven services • API design and service integration • Python-based AI services • Agent workflows • RAG pipelines • Execution validation • Production monitoring and observability
Featured System
AI Policy Governance Platform
Enterprise AI control plane with pluggable policy enforcement, dual-checkpoint validation, full audit trails, and human-in-the-loop workflows.
Architecture: Event-driven • Microkernel (plugin-based) • Policy-gated orchestration
Built for: Regulated industries requiring auditability, compliance, and controlled AI execution.
Production Use Cases: Finance: MNPI firewall, data redaction, client communication review • Healthcare: HIPAA compliance (future) • Government: Data sovereignty enforcement (future)
Other Systems
Agentic Finance Platform (Constrained)
Constrained planner–executor API for regulated finance: the LLM proposes a plan (tool calls); validation and execution are deterministic and auditable. Clear audit trail, no black-box execution, governance plug-in before any tool runs.
Trading Platform
Simulated event-driven domestic equities trading platform: trade booking, blotter, positions, and P&L. Exposes a REST API and an MCP server for agentic workflows.
API Gateway
API Gateway for multi-model LLM orchestration with circuit breakers, retry logic, adaptive rate limiting, and intelligent fallback routing. Handles request validation and traffic shaping for production AI workloads.
Technical Work and Insights
ADRs
├─ Policy Outcome Model Design
Framework for modeling and evaluating policy outcomes in AI governance systems.
├─ Sync vs Async Communication Patterns
Decision framework for choosing synchronous vs asynchronous communication in distributed AI systems.
└─ Modular Monolith to Microservices Strategy
Migration approach for evolving monolithic AI platforms into distributed microservices architecture.
Technical Writing (coming soon)
└─ How the Governance Platform scales 10x → 1000x
Documenting the evolution and scaling challenges of AI governance platform.
Case Studies
├─ NLP-to-SQL Interface for Enterprise Databases
Enables non-technical users to query enterprise databases in plain English with validation and visualization, reducing analysis time from hours to minutes.
└─ RAG-Powered Document Intelligence System
Production RAG system providing instant, context-aware access to enterprise documentation with semantic search and source attribution.
Contact
Memphis, TN | Previously New York, NY