Agentic AI Solutions Engineer

Dennis Tien Donaghy

Multi-agent systems on open protocols (MCP, A2A) · frontier-model evaluation · security-first harness engineering · Kubernetes · 15+ years of financial-risk data engineering.

Current Work

Mar 2026 – Present

Technical Reviewer — Packt Publishing

Credited technical reviewer for OpenClaw AI in Production (Ken Huang): full code review of agent architectures, MCP integrations, and security boundaries against pre-publication releases.

Nov 2025 – Present

Expert Contributor — Snorkel.ai

Reproducible benchmark environments for frontier agentic models across ML, finance, and agentic domains — PyTest, Docker/Kubernetes, Terminal-Bench, Harbor.

Jun 2023 – Present

Solutions Engineer — AIML Solutions

Hardened VPS multi-agent systems with model routing, scoped permissions, and execution boundaries; RAG pipelines; deterministic containerized infrastructure.

Flagship Project

Sep 2026 · open source

triage-mesh — Security-First Multi-Agent Vulnerability Triage

Seven services: an orchestrator delegates over A2A to three LLM agents, each reaching its own MCP tool server (2026 stateless spec), with live OSV.dev intel and human-gated publication. The model is treated as an untrusted component — every guarantee lives in the harness, and every guarantee is a test.

  • Deny-by-default policy engine, schema validation at every boundary, trust-labeled untrusted text, audience-scoped service JWTs
  • 13-scenario red-team suite must fail closed in CI; Kubernetes NetworkPolicies generated from the same policy file and proven on a kind+Calico cluster (13/13 conformance)
  • One OpenTelemetry trace per assessment across all seven services
triage-mesh architecture diagram

Background

2012 – 2023

Systems Engineer, Finance & Blockchain — AIML Solutions

Financial data ingestion and analytics for derivatives, crypto, and market data; QuantConnect LEAN backtesting; PostgreSQL and Linux.

2008 – 2012

Data Engineer, OSINT Watchlists — Safe Banking Systems

Entity-resolution and watchlist-classification systems spanning OFAC, HM Treasury, EU, and UN lists; large-scale financial-risk pipelines for compliance workflows.

Education

  • UT Austin, McCombs — Postgraduate Certificate, AI & ML for Business Applications (2025, GPA 4.22 weighted)
  • New York University — BA, Economics

Skills

Multi-agent systemsMCPA2AClaude CodePythonFastAPIPydanticDockerKubernetesHelmTerraformPostgreSQLpgvectorGitHub ActionsOpenTelemetryLangChainSQLC++