Job · Anthropic

Research Engineer, Post-Training Model Evaluations

Investigate model quality during production post-training, maintain evaluation coverage and explain regressions to research teams.

Needs a fresh check

San Francisco, CA or Seattle, WA

Application deadline: Not stated

USD 500,000–850,000/year (salary; 2026-10-05). Published annual salary range; employer determines level.

This record is historical or needs another check. It is excluded from verified-open recommendations. Read the institution’s current source before applying.

What the institution asks for

Experience designing and analyzing ML evaluations at scale; strong Python and production-system skills.
Statistics and experimental design are additional strengths. Bachelor’s degree or equivalent experience; office attendance expected.

ProfRod’s suggested preparation

Understand what this work involves

Practice the paired comparisons used to investigate changes in post-training evaluation results.

Did model A really beat model B?

Write a paired-comparison memo

Predict the difference before recomputing the saved results. Name the sampling unit, interval and one limit; keep the notebook output with your memo.

Continue the exercise

Keep it on your desk

Your free account saves this entry. Saving does not apply to the institution or subscribe you to alerts.