AI Engineer — Agentic Tutoring Systems

LearnVector Inc.; Mountain View (CA); On-site; USD 180,000 - 280,000; Full time

Job summary

LearnVector Inc. in Mountain View, CA is seeking an AI Engineer to build the agentic core of our product. You will design multi-step tutoring loops, memory, and planning over long-horizon learner relationships, and own systems end to end from design to evaluation.

You will work closely with Andrew Ng and the founding team, shipping models that understand each learner, verify that generated teaching is correct, and drive iteration with real learner data.

Qualifications

• Experience shipping LLM systems in production.
• Strong Python and/or TypeScript/Node engineering skills.
• Ability to translate fuzzy product questions into measurable systems.

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 what 'this session taught something' means operationally.
• Design guardrails and verification layers so generated content and tutor claims meet a trusted brand bar.
• Work daily with the founding team, including Andrew Ng, on the hardest product questions and how to measure success.

Skills

AI-native development

LLM APIs

Python

TypeScript/Node

End-to-end services

Tools

Claude

OpenAI API

Memory architectures

Job description

LearnVector Inc. in Mountain View, CA is seeking an AI Engineer to build the agentic core of our product. You will design multi-step tutoring loops, memory, and planning over long-horizon learner relationships, and own systems end to end from design to evaluation.

You will work closely with Andrew Ng and the founding team, shipping models that understand each learner, verify that generated teaching is correct, and drive iteration with real learner data.