I lead engineering for Proma.ai at Growthzilla. Proma.ai is an AI productivity platform built by a remote US-based team. My role spans product architecture, implementation, deployment, and iteration.

This case study covers only public information. It describes the engineering approach, not private metrics or internal implementation details.

My role

Lead engineering across full-stack product development
Design database structures and application boundaries for AI-driven workflows
Build LLM integration layers, prompt and tooling infrastructure, and product-facing AI features
Design real-time collaboration flows and state management across client and server
Own deployment and operational decisions on Cloudflare’s edge platform
Turn ambiguous product requirements into shipped, maintainable systems

Engineering focus

The core challenge is making AI features feel like dependable product features instead of demos. That means treating prompts, tools, data access, fallbacks, latency, and observability as part of the product architecture.

The work crosses several layers:

Product layer: user-facing workflows, collaboration states, and iteration speed
AI layer: LLM orchestration, tool use, prompt infrastructure, and structured outputs
Data layer: PostgreSQL-backed persistence, schema design, and product analytics needs
Infrastructure layer: Cloudflare deployment, edge runtime constraints, and production operations

Remote engineering

The team works remotely, so I optimize for clear written decisions, small reviewable changes, and enough documentation that future work does not depend on memory or meetings.

That matters more in AI product work because the product changes quickly. Clear writing keeps the system understandable while the team moves fast.

Reflection

Proma.ai is the kind of engineering I enjoy: shaping an AI product from idea to architecture to production, while keeping the system understandable enough for the team to keep evolving it.