Skip to content
View fahmidme's full-sized avatar
🔧
Building and shipping AI systems with teams.
🔧
Building and shipping AI systems with teams.
17 followers · 14 following

Achievements

Achievement: Pair Extraordinairex2Achievement: StarstruckAchievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx3

Achievements

Achievement: Pair Extraordinairex2Achievement: StarstruckAchievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx3

Block or report fahmidme

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
fahmidme/README.md

Fahmid Uddin

Forward-Deployed Product Engineer — Building and Shipping AI Systems with Teams.

Toronto-based founder-operator and hands-on engineer with 15 years of experience across frontend, backend, cloud systems, UX, infrastructure, automation, and creative technology.

I work from ambiguous operating problems through discovery, architecture, implementation, deployment, observability, and iteration.

fahmid.com · LinkedIn · X · Email

Current work

  • AI Account Executive — 650+ tracked hours delivering a client AI sales platform through workflow discovery, implementation, production releases, integrations, billing, identity, administration, and observability.
  • Optifly — AI-native travel planning with shareable itineraries, live inventory, and partner routing. Recent verified signals: 11,270 share-landing views, 13,362 itinerary loads, 201 booking clicks, and 90% plan progression.
  • Nexore / xOS — an independent AI systems studio and a self-hosted control plane used in my own product and client work for agent workflows, semantic memory, MCP tooling, isolated sessions, and permission-aware operations.

Selected engineering work

  • AgentCore AG-UI Starter — streams a Strands agent from Amazon Bedrock AgentCore into a Next.js and CopilotKit interface over AG-UI, with architecture documentation, security boundaries, CI, and a production roadmap.
  • Incident Triage API — FastAPI incident-ticket search and triage with SQLite FTS5 retrieval, grounded responses, citation validation, traces, tests, and synthetic incident data.
  • Nano Banana MCP — TypeScript MCP server for Gemini image generation on Vertex AI with GCS references, progress notifications, and long-running task support.
  • Worktree Parallel — a Codex skill for running isolated development work across parallel Git worktrees.

Earlier work

  • Gitfolio — built and sold an AI résumé-builder SaaS.
  • Metagood — first engineering hire; helped launch OnChainMonkey.
  • Decise.io — delivered ordering experiences for City BBQ, Pieology, and Chipotle.
  • LegixAI — introduced a RAG architecture that reduced LLM pipeline cost by approximately 15× and increased processing speed by approximately 20×.

Working with

TypeScript · React · Next.js · Node.js · Python · AWS · GCP · RAG · MCP · agent workflows · evals · traces

Pinned Loading

  1. agentcore-agui-starter agentcore-agui-starter Public

    Streaming Strands agents from Amazon Bedrock AgentCore to a Next.js CopilotKit UI over AG-UI.

    TypeScript 13

  2. incident-triage-api incident-triage-api Public

    FastAPI incident-ticket search and triage API with SQLite FTS5, grounded OpenAI assist responses, traces, tests, and synthetic data.

    Python 1

  3. worktree-parallel worktree-parallel Public

    Create and manage a git worktree for parallel feature development, then open the new worktree in the editor (code/Cursor) for a second Codex session.

    34 4

  4. nano-banana-mcp nano-banana-mcp Public

    TypeScript 9 5

  5. ai-screenshot-renamer ai-screenshot-renamer Public

    This project automatically renames screenshots using AI-generated descriptions. It's designed to work with macOS and uses OpenAI's GPT-4 Vision model to analyze and describe screenshots.

    Python 3