Lead Engineer, AI Platform
Lead AI quality engineering for production AI agents, building evaluation pipelines, monitoring tools, and diagnostic systems to improve reliability, speed, and cost. Develop testing datasets, analyze agent failures, and experiment with prompts and models. Requires 7+ years in software engineering, experience with AI evaluation frameworks such as Braintrust or LangSmith, and familiarity with Ruby on Rails or Python. Manage engineering priorities while remaining hands-on.