Responsibilities
- 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.
Requirements
- Experience building with LLMs in production, not just prototypes.
- Strong JavaScript/TypeScript 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.
- Experience improving AI reliability, observability, and production readiness.
Nice to Have
- Strong instincts around when to use AI vs. deterministic approaches.
- Familiarity with real-world edge cases (messy data, inconsistent inputs, ambiguous queries) and how to handle them.
Benefits
- Unlimited PTO with a three-week minimum.
- Fully covered medical, dental, and vision insurance for you, and 100% for your dependents.
- A One Medical membership.
- A gym or fitness stipend of up to $150 per month.
- One-to-one donation matching of up to $1,000 per year.
- Twelve weeks of paid parental leave after the birth or adoption of a child.
- Work from home.
- Three offsite retreats per year to get together with coworkers and plan for the quarter ahead.
Work Arrangement
Hybrid
Team
Team size: small. Structure: small team of humans (and one owl) working together to do big things
Additional Information
- Not sure if you’d be the right fit? Apply anyway! We’d love to see your application.
- We are an equal opportunity employer and a pleasant and supportive place to work.
- ReadMe is open to hiring folks fully remote in the US, hybrid, or in-person at our New York or San Francisco HQ.
