Applied AI Engineer · Boston, MA

I ship production AI systems, end to end.

Architecture, code, infrastructure, and operations — built and run solo, on my own infrastructure. A live AI SaaS with paying subscribers and a ~40-service autonomous agent fleet, on top of a corporate finance career.

~40
production services, always on
2 SaaS
products built end-to-end
13
languages, multi-currency billing
$100M–$3B
M&A targets evaluated

#What I've built

Synthesis AstrologyLIVE

Founder & AI Engineer · paying subscribers · 2025–present

A production AI SaaS built and operated solo. Multi-model LLM pipeline (Anthropic Claude + open-weight models) with retrieval-augmented generation, structured outputs, and deterministic validators that catch hallucinations before users ever see them.

The hard part isn't generating text — it's gating it. Every paid reading passes claim-level validation against computed source data before it ships.

Next.js/React/TypeScript front end, Python/FastAPI services, PostgreSQL + Redis, Stripe subscriptions with multi-currency pricing and 13-language i18n — fully self-hosted on Linux.

LLM pipelineRAGhallucination gating Next.jsFastAPIPostgreSQLStripe

Self-hosted multi-agent AI infrastructure

Independent · 2024–present

~40 always-on services across Linux VPSs on a Tailscale mesh: autonomous Claude-based agents running real operations, data, and content workflows — with error handling, budget controls, health checks, and alerting, because unattended agents without guardrails are a liability.

Custom MCP servers, RAG over PostgreSQL/pgvector, and a LiteLLM multi-model routing gateway (Anthropic + NVIDIA NIM + local Ollama) with hard per-model spend caps.

AI agentsMCPLiteLLM pgvectorobservabilityNginx · systemdCI/CD

Synthesis BenefitsLIVE

Founder & Full-Stack Engineer · 2026–present

Healthcare-adjacent SaaS: a dental-practice intelligence platform. Node/Prisma on PostgreSQL (70+ table schema), role-based access control, audit logging, Stripe billing — built end-to-end.

NodePrismaPostgreSQL RBACaudit logging

#How I work

  • AI-native by default. I direct AI as my implementation team — and stay accountable for everything that ships: real infrastructure, production code, paying customers.
  • End-to-end ownership. From first ambiguous requirement to deployed, monitored system. No hand-offs.
  • Production over prototypes. Validators, evals, guardrails, alerting — the unglamorous parts that make LLM systems trustworthy.
  • Business fluency. I evaluate every build through risk, cost, scalability, and ROI — not just technical execution.

#Finance background

#Stack

PythonFastAPITypeScript React / Next.jsNode.jsPostgreSQL / pgvector RedisLinuxNginxsystemd Anthropic API / Claude CodeMCP / tool use RAGLiteLLMStripe REST APIsGit · CI/CD