Profile cover
X

AI Formative Assessment Item Generator

Xavier Tanaka

Full-time · Job · New_York

About the role

Formative assessment — low-stakes checking-for-understanding throughout a lesson rather than high-stakes testing at the end — is the pedagogical approach with the strongest evidence base for improving learning outcomes. The bottleneck is item creation: writing good multiple-choice questions, open-ended prompts, and drag-and-drop exercises that actually measure understanding rather than recall takes skilled instructional designers 15-30 minutes per item. Our adaptive learning platform serves 3.2 million learners across K-12 and corporate training contexts. Formative assessment item generation is the capability that lets us build truly adaptive curricula: instead of recycling a fixed item bank, generate fresh assessment items calibrated to each learner's demonstrated knowledge state, targeting the specific concepts where their understanding is weakest. You'll lead assessment item generation engineering: designing generation prompts and models that produce pedagogically valid assessment items, implementing psychometric quality filters that catch items with obvious correct answers or ambiguous distractors, and building the item calibration pipeline that estimates difficulty and discrimination parameters from learner response data.

Responsibilities

  • Design assessment item generation system producing multiple question types calibrated to specific knowledge states
  • Implement pedagogical quality filters detecting items with flawed distractors, ambiguous wording, or obvious answers
  • Build psychometric calibration pipeline estimating item difficulty and discrimination from learner response data
  • Develop concept targeting ensuring generated items probe specific knowledge gaps rather than adjacent competencies
  • Create item diversity controls preventing stylistic repetition across items in the same assessment sequence
  • Validate item quality with instructional designer review as primary accuracy benchmark

Requirements

  • 6+ years in NLP engineering with educational technology, assessment design, or content generation experience
  • Understanding of formative assessment pedagogy, item writing best practices, and psychometric principles
  • Strong Python and LLM-based text generation skills
  • Experience building generation systems with quality filtering and calibration pipelines
  • Ability to collaborate with learning scientists and instructional designers on quality standards

Benefits

  • Fully remote with flexible schedule
  • Comprehensive health benefits
  • $4,000 annual professional development budget
  • Mission-driven work improving learning outcomes
  • Equity participation

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$130k – $160k / year

AI Expertise

Automation & AI Workflows NLP & Prompt Engineering

Skills

python pytorch hugging face openai api fastapi sql

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile

Interested in this role? Create your free profile to apply.

Apply — create free profile