Proma.ai Engineering

Lead engineering work on an AI productivity platform: LLM integration layers, real-time collaboration, database design, and Cloudflare deployment.

Overview

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

This case study is intentionally public-safe. It focuses on the engineering shape of the work rather than private product 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/tooling infrastructure, and product-facing AI features
  • Design real-time collaboration flows and client/server state management
  • 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 for AI product work because the product surface changes quickly. Good remote execution keeps the system understandable while still letting the team move fast.

Reflection

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