AI Engineer: Build Agentic Tutoring Systems

Uncover; Mountain View (CA); Hybrid; USD 150,000 - 190,000; Full time

Job summary

LearnVector, founded by Andrew Ng, is building a trustworthy AI guide for learning and is on-site in Mountain View, California.

You will design and implement the agentic core, develop the evolving learner model, build evaluation harnesses, and implement guardrails for safe, useful tutoring. You will work closely with the founding team to define what the AI tutor should do and how we measure success.

Qualifications

• 3+ years as a software engineer with hands-on experience building with LLM APIs (Claude, OpenAI, or similar).
• Experience shipping and operating LLM systems in production, including evaluating them.
• Strong Python and/or TypeScript/Node engineering skills; comfort owning services end to end.
• Ability to turn a fuzzy product question into a measurable system and ship without heavy oversight.

Responsibilities

• Design and build the agentic core: multi-step tutoring loops, tool use, memory, and planning over long-horizon learner relationships.
• Build the learner model—the evolving, evidence-backed representation of what each learner knows, wants, and responds to.
• Build evaluation harnesses for conversational quality and teaching quality, and drive iteration; define success metrics.
• Design guardrails and verification layers so generated content and tutor claims meet a bar a trusted brand requires.
• Work daily with the founding team, including Andrew, on the hardest product questions: what should an AI tutor do, and how do we know it's working?

Skills

Python

TypeScript/Node

LLM APIs

End-to-end ownership

Production systems

Job description

LearnVector, founded by Andrew Ng, is building a trustworthy AI guide for learning and is on-site in Mountain View, California.

You will design and implement the agentic core, develop the evolving learner model, build evaluation harnesses, and implement guardrails for safe, useful tutoring. You will work closely with the founding team to define what the AI tutor should do and how we measure success.