Erik Mejia
I work with founders, CTOs, and engineering teams to turn AI prototypes into reliable product features. I help decide what should exist, map the workflow, design the interface, write and review code, define evals, modernize AI development practices, and ship the system into production.
Proof
Products that show how I think and build
Flowcost and Didastik are products I own and build from the ground up. They show the same work I bring into client teams: turning messy AI capability into clear workflows, durable architecture, and product behavior users can trust.
Retainer
Q2 availability
AI Product Engineer
Monthly
$10,000
Minimum
3-month engagement
Where I help
Production feature builds
Ship AI product features that move beyond demo quality: copilots, assistants, internal tools, agent workflows, and AI-powered product surfaces.
Workflow architecture
Map the product flow, model choices, retrieval, tools, handoffs, infrastructure, cost, latency, and failure paths before the team commits build time.
Quality, cost & reliability
Define what good looks like, inspect failures, tune routing and retrieval, and reduce the reliability risks that make AI systems hard to trust.
AI product UX
Design AI behavior so users understand what the system is doing, trust the output, recover from mistakes, and stay in control.
RAG & knowledge systems
Turn company docs, data, and domain knowledge into grounded retrieval workflows with clear source selection and quality checks.
AI team tooling
Help your team use Codex, Claude Code, Cursor, Flowcost, and related tools inside real product and engineering work.
Client signals
What product leaders notice in the work
The pattern is consistent across leadership and product roles: reduce ambiguity, make AI work buildable, and keep the path tied to shipped product.
CEO perspective: turn a loose AI idea into a shippable direction
"Erik helped us move from a loose AI product idea to a clear, shippable direction. He brought rare range across product strategy, UX judgment, and engineering follow-through."
Product perspective: modernize the codebase and AI tooling
"Erik helped the team modernize the codebase for AI-assisted development, trained us on Cursor, and brought clearer judgment around model selection and context engineering."
Engagement
How the engagement works
The retainer is built for teams that need direct execution plus better AI product judgment. I work inside your existing tools, turn unclear work into concrete decisions, and help the team build better while we ship.
01
Embed in the real context
I get into the product, codebase, data, team chat, GitHub, docs, and planning tools so decisions are grounded in the actual system, not a workshop version of it.
02
Choose the highest-leverage work
Each week, we pick the AI product gaps, brittle prototypes, unclear workflows, or team tooling blockers that matter most. I turn them into a concrete path and execute where hands-on work is needed.
03
Ship and transfer the practice
Each cycle should leave behind shipped product, clearer architecture, better evals, stronger AI development habits, or a sharper decision about what not to build.
Book
Book a call
If this sounds aligned, pick a time below. I use the first call to understand what you are building, where the AI work is stuck, and whether I can help directly.