About the role

We build AI-powered content products, and our engineering team ships through orchestrated AI agents rather than hand-typed code. We are looking for an engineer who already works this way: someone who uses coding agents daily, verifies their output like it is their own code (because it is), and ships real features at a pace traditional teams can't match.

This role is less about how fast you type and more about how well you think, verify, and follow through. You will work alongside senior engineers who decompose the big problems. Your job is to take a well-scoped feature and drive it to done, agents in hand.

The one-line test: given a clearly specced feature and a capable coding agent, can you ship it to production, correct and reviewed, in days instead of sprints? If yes, apply.

This is an on-site position. We move fast, pair tightly, and think best in the same room.

A note on experience: the years-of-experience bar is a guideline, not a gate. If you have built things with agents that made you dramatically faster, we want to talk, even if you are earlier in your career. Demonstrated agentic output beats a long resume.

What you'll actually do

Ship well-scoped features across a modern full-stack TypeScript codebase, from spec to production.
Drive coding agents through the build: prompt, review, run, fix, and own the result.
Grow into decomposition with senior mentorship: start from clear specs, learn to turn fuzzy asks into executable plans.
Build small automations and workflows that remove repetitive work for you and the team.
Work on the product surfaces around the AI core: the app, the APIs, and the data flows that deliver LLM output to users.
Keep the bar high on correctness, security, and maintainability, even at speed.

Must-haves

Behavioral

Starts in the customer's shoes. Before you build, you ask who is stuck and why. You build for the person behind the ticket, not the ticket, and it shows in what you ship.
Runs toward the frontier. The pace of AI excites you. New models and tools land every week, and you treat each one as a chance to get better at your craft, not as a threat to it.
Agents are your default way to build. Daily, fluent use of Claude Code, Cursor, or equivalent. You reach for an agent first and your keyboard second.
Verifies relentlessly. You read what the agent produced, run it, and own the result. No blind merges.
Output measured in shipped impact, not effort. You ship features, not lines.
Curious and fast to learn. New model, new tool, new pattern: you try it the week it lands.
High agency. Asks sharp questions early, then pushes things to done without hand-holding.

Technical

Solid TypeScript on both server and client, typically 2 to 5 years building production software.
Working command of a modern Node backend framework and a modern React frontend.
Relational database and ORM basics, and clean REST API habits.
Has deployed to a cloud platform (any provider) and can read code you didn't write.
Has built something real with an LLM API: a feature, a tool, or a serious side project.
Testing and debugging habits that survive contact with production.

Good-to-haves

Built custom agents, harnesses, or automations that go beyond off-the-shelf tool use.
Worked in a monorepo with shared packages between back and front end.
Prompt engineering beyond the basics: structured output, evals, cost and latency tuning.
Real-time features, scraping or data pipelines, or RAG experiments.
Open-source contributions or a public portfolio of shipped work.

How we work

Ship-daily culture, tight feedback loops, and AI-orchestrated review. We give you the most capable models, generous token budgets, and the autonomy to use them. Bring the judgment.

How to apply

Email careers@vmdsolution.com with the subject line "Application: Full Stack Engineer". Skip the cover letter. Send the thing you are most proud of building with agents: a repo, a demo, a screencast, or a short write-up of how you built it. Show us the loop you run, not just the result.

Full Stack Engineer