ceena.dev

Hi, I'm Sina Naeemi —

Full-Stack Product Engineer who builds AI-assisted workflows.

I build AI-assisted systems that turn unstructured business inputs into structured, reviewable workflows.

Resume GitHub Email
See the workflows I've built

About

A bit about me

I'm an early engineer at GRiDD Technologies, where I built GNet Connect from the ground up — a B2B transportation platform spanning reservations, documents, partner discovery, support workflows, and internal operations.

I focus on AI-assisted operational systems that convert unstructured business inputs into structured, reviewable workflows — across the full stack, from React/Next.js UIs to backend APIs, SQL/Redis data systems, and retrieval pipelines.

B.S. in Computer Science, UC Riverside (2024). Scroll down to explore the workflows I've built, rendered as interactive diagrams.

Experience

Where I've worked

Product / Full-Stack Engineer · GRiDD Technologies / GNet Connect

2024 — Present

Early engineer who built GNet Connect from the ground up — a B2B transportation platform for reservations, documents, partner discovery, support workflows, and internal operations.

  • Built and shipped full-stack product features across React/Next.js, TypeScript, backend APIs, SQL/stored procedures, Redis/RediSearch, and internal admin tools.
  • Designed AI-assisted operational systems built around human review, uncertainty surfacing, and feedback loops — including an AI email intake pipeline for reservations and a Gmail support agent.
  • Worked directly with the CTO, CEO, support team, and customers to turn operational problems into data models, UI flows, backend behavior, and shipped product.
ReactNext.jsTypeScriptNode.jsPythonSQLRedisMCPLLMs

Workflows

Systems I've designed & built

These are interactive — drag to pan, use the controls to zoom. Each diagram maps a workflow I designed end to end.

AI Email Intake for Reservation Workflows

The hard part isn't extraction — it's operating reliably on messy input: classifying intent, applying scoped account context, validating against the reservation schema, surfacing missing fields instead of guessing, and keeping a human in control.

Gmail Support Agent for Internal Operations

A support reply is a context-assembly problem, not a generation one. The agent classifies the issue, gathers account and reservation context via MCP tools, retrieves similar resolved emails, and grounds a draft the agent reviews and sends.

Case Studies

What I've built

AI Email Intake for Reservation Workflows

Turning unstructured customer emails into structured reservation drafts — with intent classification, schema validation, explicit missing-field detection, human review, and account-level memory.

LLM WorkflowsSchema ValidationHuman-in-the-LoopAccount Memory
Read case study →
Gmail Support Agent

Treating a support reply as a context-assembly problem: classify the issue, gather account and reservation context via MCP tools, retrieve resolved precedents, and ground a draft for human review.

MCPRetrievalContext AssemblyGmail Add-ons
Read case study →

Skills

Tools I work with

Frontend

ReactNext.jsTypeScriptJavaScript

Backend

Node.jsPythonREST APIsWorkflow Design

Data

SQLRedisRediSearchData ModelingStored Procedures

AI / Retrieval

LLM WorkflowsEmbeddingsRetrievalPrompt DesignMCPHuman-in-the-Loop

Tools / Platforms

GitHubGmail Add-onsAzureDockerOpenAIAnthropic

Contact

Let's talk

I'm open to interesting problems and good conversations. The fastest way to reach me is email.

sina0naeemi@gmail.com GitHub LinkedIn