Senior Software Engineer · Technical Lead
Agents, RAG, and multi-provider LLM architecture — engineered with the same rigor I bring to enterprise backends: safety, cost control, and clean abstractions that survive contact with production.
I'm a senior software engineer and technical lead who moves fluidly across the stack — backend architecture, frontend engineering, DevOps, and cloud — with more than a decade shipping software for startups, product teams, and enterprise clients.
For the last few years my focus has been AI: designing agent architectures, retrieval pipelines, and LLM integrations that are actually safe and affordable to run at scale. I care about the unglamorous parts — PII boundaries, token budgets, audit trails, provider fallback — because that's what separates a demo from a system people can trust.
I like modernizing legacy systems, mentoring engineers, and translating between business and code. I work well with clients directly, and I hold a high bar for craft.
AI · RAG · Agents
A single interface that swaps between Anthropic, OpenAI, Azure, Gemini, and local models — with per-tenant encrypted keys, model selection per task, and graceful fallback. No lock-in, no rewrites when providers change.
PII redaction at the prompt boundary, fail-fast token-budget middleware that blocks over-limit requests before they hit the API, and an immutable audit trail logging provider, model, tokens, cost, and latency on every call.
A dedicated processing agent, separated from the API layer, so sensitive data is handled in isolation and never exposed to the application tier — a zero-PII path by design.
Production LLM pipelines processing thousands of documents — structured JSON-schema output, server-side web search, batch APIs for major cost savings, and provider-agnostic orchestration with anti-misinformation gates.
Model Context Protocol servers and a published Claude Code skill — extending AI assistants with custom tools and reusable, shareable capabilities.
Architecture Decision Records, agent instruction files, and curated runbooks that make AI-assisted development repeatable and reviewable across a team — not just a solo trick.
Selected Work
Civic-tech · data platform
An LLM pipeline that classifies news sources, extracts structured claims from thousands of articles, and evaluates public-record data — with cost-optimized batch processing and fact-check gating.
Construction · vertical SaaS
A vertical SaaS with an AI copilot — camera analysis, document intelligence, and streaming chat — built on a provider-abstraction layer with per-tenant budgets and PII redaction.
Data governance · SaaS
A cloud data-quality service with a dedicated processing agent isolated from the API, ensuring sensitive records are analyzed without ever crossing into the application layer.
Energy · enterprise BI
Enterprise business-intelligence dashboards and data integrations for a large energy utility — embedding analytics into operational tooling for non-technical stakeholders.
Fintech · payments
Role-based access control, permission-driven UI, and data-quality frameworks for a global payments organization — with security hardening and enterprise UAT.
Invoicing · SaaS
A multi-tenant electronic-invoicing platform integrating with tax-authority systems — certificate management, XML storage, quotas, and subscription handling.
Client and product names withheld by design.
Own SaaS ecosystem
Recent
Enterprise data & analytics consultancy
Multi-year
E-commerce, fintech, edtech, mobile
Earlier