Magic, San Francisco +1
The Evals team measures the performance and capabilities of internal and external models, helping teams across Magic make informed decisions. The team supports pretraining, RL, data, inference, and product, and sits on the critical path of many of the company's most important decisions.
As a Member of Technical Staff on Evals, you will develop new benchmarks and evaluation methodologies, run data ablations, assess dataset quality, and investigate whether our measurements accurately reflect model performance.
Sweating the details matters on this team. Many benchmarks, papers, and open-source evaluation frameworks contain subtle bugs or flawed assumptions that lead to misleading conclusions. We care deeply about correctness, reproducibility, and measurement quality.
Magic’s mission is to build safe AGI that accelerates humanity’s progress on the world’s most important problems. We believe the most promising path to safe AGI lies in automating research and code generation to improve models and solve alignment more reliably than humans can alone. Our approach combines frontier-scale pretraining, domain-specific RL, ultra-long context, and inference-time compute to achieve this goal.
Magic strives to be the place where high-potential individuals can do their best work. We value quick learning and grit just as much as skill and experience.
BuildSan Francisco
Pay not posted
Posted Aug 30, 2026
JarminSan Francisco, California
$200K–$300K / yr
Posted Aug 17, 2026
checked 2 days agoHandshakeSan Francisco, CA +3
$200K–$350K / yr
Posted Sep 29, 2026
$210K–$320K / yr
Posted Oct 30, 2025
ProfoundNew York, New York +1
$230K–$325K / yr
Posted 16 days ago
$240K–$290K / yr
Posted 2 days ago
Source: the Magic Ashby job board. We last checked this job 2 h ago. We first saw it 4 days ago. A job on a job board does not always mean that the team interviews people now. We found this job board in a public list. We did not yet compare it with the careers page of the company.
No one has reported an interview at Magic yet. Did you interview there? Add the questions.