AI Engineer

Overview

📍 Locations:
San Francisco (Hybrid), New York (Hybrid), Columbus (Hybrid), or Remote (US)

We’re hiring an AI Engineer to shape how AI shows up across Read Me’s product: from how developers explore and understand APIs to how companies author and maintain their documentation. We’re at the forefront of a major shift in developer experience.

We’re a small team of humans (and one owl) working together to do big things — and that’s where you come in. In this role you’ll have a transformational impact on Read Me across both the trajectory of the business and our thriving culture.

Read Me helps more than 5,000 leading startups and tech companies build beautiful, personalized, and interactive developer hubs. If you’ve ever visited the developer docs for Pager Duty, Samsara, or Nvidia, you’ve used Read Me!

We’re providing tools for teams to build a better developer experience and make their products and APIs easier to use. We’ve got great support from our investors at Accel who led our Series A, and our interview process reflects the open, caring, and whimsical culture we want to maintain as we scale.

This isn’t a feature team where a PM hands you tickets. You’ll help decide what gets built, why it matters, and how it works end-to-end. You’ll work on systems that are already live across thousands of developer hubs and define what they become next.

Read Me's AI surface spans three bets we're doubling down on:

• Documentation that writes itself. AI that watches code change and keeps docs current — from PR-level suggestions to org-wide audits that surface and fix quality issues at scale.
• Answers, not search results. A conversational layer embedded directly in developer hubs, grounded in real docs, that gives developers the right answer instead of a list of links to dig through.
• APIs that are agent-ready. As AI agents increasingly talk to APIs, the structure and clarity of those specs matters more than ever. We're building the systems that make APIs understandable by both humans and machines.

Day to day, you’ll:

• Design end-to-end AI systems: combining LLMs, embeddings, retrieval pipelines, and structured outputs into reliable product features.
• Build grounding and retrieval layers: indexing docs, OpenAPI specs, and customer data to support accurate, context-aware generation.
• Define evaluation systems: measuring accuracy, latency, cost, and user impact; building feedback loops to continuously improve quality.
• Handle real-world complexity: malformed specs, inconsistent docs, edge-case APIs, and ambiguous user queries.
• Make architectural tradeoffs: latency vs. quality, cost vs. coverage, deterministic vs. generative approaches.
• Own production reliability: observability, fallbacks, rate limiting, and safe degradation when systems fail.
• Work across the stack: from model orchestration and backend systems to the UI surfaces that expose them.

• Want to own meaningful systems end-to-end, not just features.
• Care deeply about developer experience and documentation quality.
• Enjoy working on problems where AI, APIs, and product design intersect.
• Have strong instincts about what makes AI actually useful and where the industry is headed.

• Experience building with LLMs in production, not just prototypes.
• Strong JavaScript/Type Script or Python experience.
• Experience working with:
• Embeddings and retrieval systems (RAG).
• Prompting and structured outputs.
• Evaluation and iteration of AI systems (quality, latency, cost).
• Comfort working with APIs and structured data (JSON, OpenAPI, schemas).
• Experience designing and shipping end-to-end systems, from backend pipelines to user-facing product surfaces.
• Strong instincts around when to use AI vs. deterministic approaches.
• Experience improving AI reliability, observability, and production readiness.
• Familiarity with real-world edge cases (messy data, inconsistent inputs, ambiguous queries) and how to handle them.

• Build a deep understanding of Read Me’s AI systems and product surfaces.
• Ship meaningful improvements to existing AI features.
• Get close to real customer workflows and…