Staff AI Research Engineer – Frontier Judgment & Evaluation

Crucibl Co.; San Francisco (CA); Hybrid; USD 180,000 - 260,000; Full time

Benefits offered by this job

Hybrid Schedule

Full Health Coverage

Equity

Lunch & Snacks

Job summary

Crucibl in San Francisco is building the next generation of enterprise AI. You will explore how frontier models reason in high-stakes decisions and design evaluation methods to test and ship robust solutions.

Join a small, elite team that shapes product direction, collaborates with founders, and operates in a fast-growing, equity-driven environment. We value published research, practical impact, and high-ambiguity problem solving.

Qualifications

• Undeniable signal of excellence: published research, frontier lab experience, or novel technical contributions.
• Deep understanding of how LLMs reason, fail, and can be evaluated.
• Strong fundamentals in ML, statistics, or NLP.
• Ability to convert open questions into testable hypotheses quickly.

Responsibilities

• Push the frontier of judgment by researching how frontier models reason and where they fail.
• Build evaluation frameworks that measure true model judgment and reveal real failures.
• Partner with founders to shape technical vision and roadmap.
• Set rigorous, applied research standards in an AI-first org.

Skills

Frontier models

LLM evaluation

Research experience

ML/NLP fundamentals

Hypothesis testing

Job description

Crucibl in San Francisco is building the next generation of enterprise AI. You will explore how frontier models reason in high-stakes decisions and design evaluation methods to test and ship robust solutions.

Join a small, elite team that shapes product direction, collaborates with founders, and operates in a fast-growing, equity-driven environment. We value published research, practical impact, and high-ambiguity problem solving.