Job Description
Manicule is building AgentRel: systems that help companies become sources AI agents cite and recommend.
We’re solving two problems: understanding how LLMs choose which content and brands to surface, and using AI to produce genuinely useful technical conten, not slop.
I’m looking for an intern who already finds this interesting. Maybe you’ve tested why ChatGPT cites one source over another, built your own agents, or obsessed over making model output less generic. No professional experience is required, but TypeScript knowledge and proof of curiosity are.
What you’ll do
- Ship TypeScript features used by real customers.
- Improve how our agents gather context, draft content, and learn from human review.
- Turn editorial judgment into workflows and quality checks.
- Work directly with founders and customers.
You won’t spend three months on a fake intern project. You’ll ship to production and take on responsibility as quickly as your output earns it.
First 30 days
Probably the highest thing on my list is building an extremely durable and powerful context system.
Our agents need to gather context from dozens of sources, from a company’s Slack and Linear to GitHub and its docs, and use it to produce amazing work on the first try. These sources contain huge amounts of noisy, constantly changing information. You’d build, eval, and improve this production infrastructure.
Bonus points if you’ve worked in context management before.
Details
- Up to three months in person in San Francisco.
- Remote may be possible for the first month.
- Possible full-time offer.
- Meals at the office.
- Unlimited GPT and Claude, including Fable.
Optimize Your Resume for This Job
Get a match score and see exactly which keywords you're missing
Job Details
- Category
- Software
- Employment Type
- Internship
- Location
- San Francisco, CA (Hybrid)
- Posted
- Compensation
- $100,000 - $150,000 per year
About Manicule
Manicule is an AI-native technical documentation agency. We own technical documentation end-to-end for developer tool companies, including information architecture, messaging, writing, design, and QA. Agents handle the mechanical parts like code verification and auditing at a scale and speed no human team can match, while humans refine the thinking and make the docs actually good. We're at $15K MRR and profitable, with clients like Supermemory, Greptile, Reducto, and Rootly. Supermemory's docs drove a 30% improvement in answer success rate and went viral on Twitter, all shipped in 23 days. Every dev tool founder knows their docs are broken but simply don't have the time to fix them. The old solution was hiring a full-time technical writer who understands engineering, marketing, and devrel. That role is really hard and expensive to hire for, so docs stay broken. Naman started freelance writing for developer tools 3 years ago and realized that you can't one-shot docs. They require tight feedback loops with the engineering team, multiple review cycles, and real product understanding. When he worked with Supermemory, they had two products that sounded identical to customers. He got on calls with the CEO, figured out the right positioning for each product, and restructured the entire docs around it. That kind of work requires judgment and context that agents simply don’t have. On the other hand, testing every code snippet against a live API, auditing hundreds of pages for broken links, and drafting from OpenAPI specs is grunt work that agents do in minutes. The insight behind Manicule is that good documentation requires both, and nobody has packaged them together. Shreyans was a founding engineer at Supermemory, saw the impact of good docs firsthand, and joined Naman to productize Manicule. We're now a team of 5, building toward that vision. Thousands of AI startups are launching dev tools every month, and docs are the single biggest asset they're all neglecting.
More Roles at Manicule
Similar Software Roles
Found this role interesting?