The role involves building AI-first products, features, and evaluations by bridging the gap between model capabilities and real-world product experiences. Responsibilities include designing, testing, and optimizing system prompts to shape model behavior across consumer and API products. The position requires building and maintaining comprehensive evaluation suites to ensure model quality and consistency during releases. Professionals in this role will collaborate with product, research, and safeguard teams to maintain safety and quality standards. Additionally, the work entails contributing to infrastructure frameworks and mentoring team members on best practices for prompt engineering.

Candidates must possess at least five years of software engineering experience using Python or similar languages. A demonstrated background in LLMs, prompt engineering, and evaluation methodologies is required. Applicants should have strong communication skills and the ability to manage multiple concurrent projects. A bachelor’s degree or an equivalent combination of education, training, and experience is the minimum educational requirement.