Edward Federbush

AI Product Engineer·Three Startups, Two Acquisitions

I've been building software products since 2001, from first engineering hire under the founding CTO at GLG through co-founding two acquired startups. Today I build AI into the center of a product: an assistant that runs a real business from first call to paid invoice, with every model chosen by measurement and evals behind every change. The through-line: I build directly with the people using the product — from teams inside Fortune 500 companies to small field-service operators.

Experience

Wipjet

AI-Native Field-Service Platform

Founding Engineer · 2025 – Present

A multi-tenant platform that runs a home-service business from first call to paid invoice, with one AI assistant that follows the work the whole way.

One assistant across the lifecycle: it takes the inquiry, drafts and sends the estimate from the shop's own rates, answers questions over live schedule, parts, and invoice data, and drafts the invoice — a human confirming anything that touches money or a customer.
Tools designed for a model, exposed in the app and through a remote MCP server, so an owner can run the business from Claude; tenant isolation by Postgres row-level security under every tool call.
Each model chosen per task from head-to-head bakeoffs; evals gating every prompt and model change, including a 59-case prompt-injection suite; every call traced and attributed per business.

Read the full write-up →

Independent

Product Engineering & Consulting · 2021 – Present

Founder, UserBuilders · 2026 – Present

A small software studio for publicly funded programs. UserBuilders gives nonprofits, local agencies, and research teams the software they need to build a program, run it, and report on its results.

Product Experience Consultant, Capital One · 2021 – 2022

Consulting engagement: brought in by the head of a new unit to research and design its first product, a co-brand credit product for direct-to-consumer e-commerce merchants; the work grew into designing an enterprise-wide platform to host it.
More than 40 hours of interviews with merchants and consumers, competitive research, and rounds of prototypes, through handoff to internal engineering in a large regulated enterprise.

I also build smaller products of my own, mostly to work through new AI techniques on real problems before I rely on them elsewhere: an AI copilot for vintage-fashion resellers, an open-source starter kit for AI-ready SaaS apps, and lead and marketing automation for small businesses.

Docurated

Acquired by Quark Software (2018)

Co-Founder & Full-Stack Product Engineer · 2012–2018

Co-founded SaaS platform for enterprise sales enablement (TechCrunch Disrupt finalist); led product experience from inception through acquisition, and built full-stack across desktop, mobile, and embedded Salesforce apps.
Worked directly with Fortune 500 clients (Netflix, J.P. Morgan, IBM) on custom implementations and white-labeled workflows, and shaped the product's features around what those teams needed.

After the acquisition, took a planned break (2018–2021) following two back-to-back startups.

Private Screening Platform

Awards Voting & Festival Screenings

Founder & Engineer · 2011–2013

Built and ran a secure video screening platform used by 6,000+ Academy members for Oscar voting and 100,000+ SAG members for SAG Awards voting, plus studio screenings at Sundance and Cannes. Wound down to focus on Docurated full-time.

Boliven

Acquired by Cambridge IP (2011)

Founding Member & Full-Stack Product Engineer · 2008–2011

Employee #4 at this GLG-alumni-founded startup, which built a visual search and analytics platform over more than 100 million patents, journal articles, and press releases. Full-stack Rails role from early product through acquisition.

Gerson Lehrman Group (GLG)

Enterprise Expert Network

Engineer → Director of Product Design · 2001–2008

Founding CTO's first engineering hire at what became the world's largest expert network. Started as a full-stack engineer, building the early product on a tiny team.
Later moved into leading the product experience group, a team of ten designers, UX engineers, and researchers.

Education

Boston University — BA, Philosophy

Technical Skills

AI Engineering

Agentic systems with multi-step tool calling, structured output, and human-in-the-loop confirmation; tool design for models and remote MCP servers with OAuth; agent skills. Evals — golden sets, behavior evals against seeded data, LLM-as-judge with calibration, model bakeoffs on quality, latency, and cost. Prompt-injection defense and adversarial testing. Per-task model routing through an AI gateway. LLM observability — distributed tracing, per-tenant cost attribution, prompt caching. Voice AI, multimodal vision and image generation, streaming and generative UI. Vercel AI SDK, Model Context Protocol, Langfuse, OpenTelemetry, Retell.ai.

AI-Native Delivery

Spec-driven development with coding agents, agent orchestration and dispatch, verification designed around agent failure modes, failure-ledger feedback loops.

Full-Stack Product Engineering

React 19, Next.js 16 (App Router), TypeScript, Node.js, Ruby on Rails, Tailwind, Postgres with row-level security, Drizzle ORM, Neon, multi-tenant SaaS architecture, offline-capable PWAs, REST APIs, Chrome Extensions.

Product & UX

End-to-end product discovery and prototyping, user research and interviewing, journey mapping, wireframing, design systems, UX/UI, WCAG/ADA compliance.

Infrastructure & Delivery

Vercel, AWS (S3, SES), GitHub Actions, Playwright end-to-end testing, Stripe (payments, subscriptions, webhooks), QuickBooks Online, Clerk auth, Resend.