Senior Python Engineer: Secure Coding-Agent Benchmarks

Braintrust seeks senior software engineers to design and evaluate realistic coding-agent benchmark tasks, combining production engineering, secure software development, repository validation, test design, and careful evaluation of safety, privacy, permission, and data-integrity requirements.

You will build production-like benchmarks, define utilities, and create reference solutions while collaborating with engineering, QA, security, and client teams to improve evaluator reliability and benchmark