Model Behavior Engineer

Stack

Responsibilities

• ▹Context engineering: design, test, and iterate on system prompts, tool prompts, and context strategies
• ▹Understand and debug: live in production data (transcripts, logs, user feedback), reproduce issues, find root causes
• ▹Build evals and measurement: design eval strategies, build datasets, run evaluations, track quality over time
• ▹Evaluate and launch new models with leading research labs (OpenAI, Anthropic, Google), benchmarking quality, latency, cost, and edge cases
• ▹Drive quality priorities, working embedded with engineering and product teams
• ▹Build tooling and systems: help manage AI observability and eval platforms (e.g. Braintrust), build playbooks

Requirements

• ▹Driver mentality: treat problems as yours, bias to action
• ▹Curiosity about exploring the frontier of LLM capabilities
• ▹Analytical instinct, finding signal in noisy data
• ▹Comfortable working with data (SQL, coding agents, or other tools)
• ▹Clear communication of complex issues
• ▹Experience with LLMs, prompting, or AI products

Nice to have

• ▹Backgrounds in engineering, product, data science, research, or consulting
• ▹Built something on your own to solve a problem — side project, startup, or tool

Soft skills

What we offer

• ▹Highly competitive cash compensation, equity, and benefits
• ▹Estimated base salary for San Francisco/New York City: $98,000–$140,000 per year

About the company

Notion is the collaborative AI workspace where teams and agents think together, bringing knowledge, projects, meetings, and AI tools into one place. Millions of individuals, small teams, and large companies run their work on Notion.