InCommon
Website:
joinincommon.com
Company:
https://www.linkedin.com/company/incommonhq
Seniority: Mid-Senior level
Industries: Marketing Services
Job details:
Founding AI-Native Product Engineer — Search & AI Visibility Agent
Boring Marketing is a US-based company who is building a Search & AI Visibility agent that teams add to Slack, MCP clients, and internal workflows to understand how they show up across Google, ChatGPT, Perplexity, Gemini, Claude, and other AI-search surfaces.
We already have a working Brain API, Slack/Hermes agent runtime, crawler, public AI-visibility audit, dashboard, lead capture, visibility pipelines, and production infra. Now we need a founding engineer who can turn that into a reliable, self-serve, revenue-producing product — and who can move at agentic speed without sacrificing product judgment, correctness, or production safety.
This is not a "uses ChatGPT sometimes" role.
We're looking for someone whose default development loop is agentic: inspect the repo, plan, spin up worktrees, delegate/review sub-agents, write tests, run checks, ship PRs, and verify production behavior. You should already feel faster, sharper, and more ambitious because you build with coding agents every day.
Core requirement
You should be deeply fluent with:
- Claude Code
- Codex / OpenAI coding agents
- Cursor / Windsurf / agentic IDEs
- MCP servers and tool-calling workflows
- Worktrees, small PRs, CI loops, test-driven agent workflows
- Prompting agents with repo context, constraints, acceptance criteria, and verification plans
You know how to use agents without letting them run wild. If you can say this and mean it, you're the right person:
"I use Claude Code/Codex as my default engineering environment. I know when to let the agent explore, when to constrain it, when to split work across worktrees, and how to verify every change before it ships."
What you'll own
You'll build and harden the core loop: connect a brand → understand its market → measure visibility → find gaps → recommend fixes → ship improvements → monitor progress.
Projects include:
- Hardening the free AI-visibility audit into a dependable acquisition engine
- Improving audit latency, partial-result handling, queueing, backpressure, caching, and observability
- Building self-serve onboarding for brands, tenants, Slack, MCP, and API keys
- Creating curated MCP tools over the Brain API
- Turning raw SEO/AEO data into marketer-readable recommendations
- Building admin tools for audits, failures, spend, leads, and customer value
- Improving LLM grounding, report truthfulness, structured outputs, and evals
- Using Codex/Claude Code aggressively to ship faster while maintaining high verification standards
What excellent looks like
You're probably a fit if you:
- Are genuinely Claude Code / Codex native
- Can take an ambiguous product problem and independently ship a tested production feature
- Know how to use agents for exploration, refactors, tests, docs, migrations, and code review
- Can manage multiple worktrees/branches without losing control
- Are strong in backend systems: queues, retries, DB models, API contracts, auth, PII, observability
- Can build enough frontend to ship polished product flows
- Understand that AI-generated code must still be read, tested, and owned
- Have good taste about what should be automated, what should be manual, and what shouldn't exist yet
- Care about truthfulness: no invented report claims, fake confidence, or ungrounded recommendations
- Prefer small, shippable PRs over massive speculative rewrites
This role is not for you if you:
- "Use ChatGPT sometimes" but don't run an agentic coding loop
- Let agents generate code you don't understand
- Avoid tests, CI, or production debugging
- Need perfect tickets before starting
- Only want to write prompts
- Only want to prototype
- Can't operate in an existing codebase
Click on Apply to know more.