Manicule is building AgentRel: the systems that help companies become discoverable, cited, and recommended by AI agents.
Two problems drive the work. First, understanding how LLMs decide what content to retrieve, trust, and cite when they recommend companies. Second, using AI to create genuinely useful technical content without filling the internet with slop.
You'll work directly with customers, not close tickets from finished specs. We went from $0 to $30K MRR in two months, and you'd shape the product from here.
What you'll do:
- Build the systems behind documentation, technical content, and agent workflows.
- Research how LLMs retrieve information, choose sources, and cite brands.
- Turn editorial judgment into agent workflows, evals, and quality checks.
- Design how agents handle context across long-running jobs.
- Work directly with customers' founders, engineers, and DevRel teams.
- Own projects from the first customer conversation through production.
Who we're looking for:
- 3+ years of professional software engineering experience.
- Excellent TypeScript, and you're comfortable across the full product.
- Opinions on GEO and how LLMs discover and surface information.
- Strong views on what makes technical content useful and credible.
- You build with agents and think about context, retrieval, evaluation, and human review.
- You operate without detailed specs and want direct customer contact.
In your first 30 days, you'll build our context system: infrastructure that lets agents pull context from noisy, changing sources — Slack, Linear, GitHub, docs — and produce strong work on the first attempt. Prior context-management work is a bonus.
In-person in San Francisco; remote may be possible for the first month. Breakfast, lunch, and dinner at the office. Medical, dental, and vision. Unlimited GPT and Claude, including Fable.
Hiring is a first call, then a trial.