AI Engineer / Autonomous Systems Builder — Claude Code + Open Models ($800–$2,500/mo DOE)

We are a US-based AI company running multiple brands — AI video production, AI-powered real estate technology, and a network of medical compliance clinics. We are hiring an AI Engineer who builds with autonomous agents the way developers used to build with frameworks.

The honest pitch: work that used to cost us $100,000/year in dev contracts now ships in a week with the right person and the right stack. We are looking for that person. Not someone who "uses AI for coding" — someone who has internalized that the harness around the model is the actual product, and who treats Claude Code, Kimi K2, GLM, Minimax, and Qwen as a routed orchestra rather than competing chatbots.

WHAT YOU'LL ACTUALLY BUILD:

- Multi-agent workflows that run unsupervised overnight (planner / generator / evaluator architectures, not single-shot prompts)
- Real estate data pipelines pulling MLS, HUD records, and public sources into Supabase with webhook triggers
- Internal tools and dashboards for non-technical operators across our brands (we have a backlog)
- Custom MCP servers when none exist for what we need
- WordPress / Next.js sites cranked out fast with AI-native workflows (we have 3-4 in the pipeline right now and will pay you well to ship them)
- Voice and video automation pipelines (Whisper, Seedance, fal.ai — bonus if you've touched these)
- Whatever the brief is next week, because the work is varied and we move fast

WHAT WE PROVIDE:

- Paid access to every coding model and tool that matters — Claude Max, Kimi, GLM, Minimax, Codex, GPT, Gemini, whatever you need
- Infrastructure budget (Supabase, Vercel, Cloudflare, Runpod, VPS)
- Direct line to ownership — no project manager between you and the brief
- Long-term recurring work across multiple brands, not one-off projects
- Top performer becomes the lead and brings on junior builders under them

WHAT WE DON'T WANT:

- "I use ChatGPT for code" people
- Anyone whose AI workflow stops at copy-paste
- WordPress-only developers with no scripting depth
- AI-polished cover letters that say "I am thrilled to apply for this exciting opportunity"

HOW TO APPLY — READ CAREFULLY:

Most applicants paste AI-generated answers to questions like these. We can tell. The candidates we hire answer like people who have shipped real systems and have the scars to prove it.

Answer all nine questions below in your own words, in one sitting, without running your response through an LLM to clean it up. Short and honest beats long and polished. If your answer reads like Claude wrote it, we will assume Claude did.

1. What's the most annoying thing about Claude Code (or your daily coding agent) that you've had to work around? Be specific — what broke, what did you do?

2. Describe the last subagent, skill, slash command, or hook you built. What problem did it solve? What would you do differently next time?

3. Brief: "Pull every active MLS listing for one real estate agent, enrich each with public HUD transaction history, dump structured JSON into Supabase storage, triggered by a webhook from a form submission." Give us your rough architecture in 5–10 bullets — not the code, just how you'd stitch it. What's the hardest part?

4. Name one MCP server you've used in production (not just installed to test), and one you wish existed but doesn't.

5. Which do you reach for first for background jobs — Inngest, n8n, BullMQ, Temporal, or plain cron — and why? No wrong answer, we want your reasoning.

6. Have you actually shipped anything with Kimi K2, GLM 4.5/5, Minimax M2, Qwen 3 Coder, or any non-Anthropic frontier model? If yes — what, and how did you route between them? If no — be honest, don't make it up.

7. Tell us about a production failure. What broke, what you did, what you learned. One paragraph.

8. Send three portfolio links minimum — GitHub repos with visible commit history, live sites you built, Looms of tools you've shipped. We will look at the commit graphs.

9. One-line answers: monthly rate expectation within $800–$2,500, hours per week you can commit, time zone, and overlap with US Eastern.

We read every application that answers all nine honestly. We delete the rest.

BONUS (NOT REQUIRED, BUT NOTICED):

- Self-hosted observability (Langfuse, Helicone, claude-code-hooks-multi-agent-observability)
- Understanding of the "lethal trifecta" and prompt injection mitigation
- FFmpeg / video pipeline work
- Real estate, mortgage, or regulated-industry experience
- Public writeups, blog posts, or X threads showing you've thought publicly about agents
- GitHub commits in the last 30 days

DETAILS:

- Job Type: Full-Time
- Salary: $800–$2,500/month based on experience demonstrated in application
- Hours: Flexible, with 3–4 hours US Eastern overlap required daily