Hello, I'm David Sheppard

Engineering Leader | AI Systems Builder | Platform Architect

Engineering leader with 20+ years building cloud-native distributed systems, developer platforms, and cybersecurity products. Currently building open-source AI agent tooling, including persistent memory systems for AI-assisted development and multi-agent workflows with intelligent model routing.

David Sheppard

About Me

Engineering leader with deep experience across cybersecurity platforms, identity and access management (IAM), and cloud-native distributed systems. My career spans Fortune 100 scale and startup environments, and I specialize in connecting strategy to execution across product, engineering, and security stakeholders.

Most recently I have been building open-source AI agent infrastructure: persistent memory systems backed by vector databases, multi-agent workflows with cost-optimized model routing, and local AI workstation tooling. I bring the same engineering rigor from enterprise platform work to the AI tooling space.

20+ Years Experience
50+ Engineers Led
9000+ Customers Served

AI Agent Systems

MCP servers, vector search, multi-agent orchestration, and local LLM infrastructure

Secure Platforms

Security-first architecture for IAM, credential handling, and PII governance

Delivery Excellence

Agile + DevOps transformation, observability, incident response, DORA metrics

Open Source Projects

Open Brain

Persistent AI second brain: an MCP server backed by PostgreSQL + pgvector that gives every AI tool shared memory. Store thoughts as vector embeddings so Claude, Cursor, Windsurf, and Copilot can search by meaning, not just keywords. Local-first; you own the data.

Python MCP pgvector Ollama PostgreSQL

Agentic Lab

A two-agent LangGraph workflow with 3-tier model routing and Open Brain integration. A Researcher agent searches memory via semantic search, a Router scores complexity and picks the cheapest capable model, and an Analyst synthesizes the answer.

LangGraph Claude API Ollama Python

Local AI Workstation

Interactive setup wizard for a local AI workstation: LLMs, image generation, and video generation on any NVIDIA GPU. One command installs and configures Ollama, LM Studio, ComfyUI, and FramePack. No cloud dependency after setup.

Ollama ComfyUI CUDA PowerShell Bash

Enterprise Experience

Cybersecurity Platform

Led engineering for a cybersecurity platform serving 9,000+ enterprise customers. Established delivery guardrails, reliability practices, and DORA-based measurement.

Data Platforms

Built API-driven data platforms processing billions of records daily. Delivered $20M+ annual cost savings and protected $500M+ in revenue through secure data separation.

AI/ML Security Signals

Delivered AI/ML-powered classification and anomaly detection for suspicious access identification. Focused on secure SDLC, audit readiness, and operational resilience.

Technical Skills

AI & Agent Systems

MCP Servers
LangGraph
pgvector
Ollama
Claude API
RAG Pipelines

Cloud & Platforms

AWS
Azure
Docker
Kubernetes
Microservices
API Design

DevOps & Security

GitHub Actions
GitOps
IAM
DORA Metrics
Python
JavaScript

Get In Touch

Let's Connect

I'm always interested in hearing about new projects and opportunities. Whether you have a question or just want to say hi, feel free to reach out!

davidasheppard@outlook.com
Available on request
Plano, TX