Perplexity12.05.2026

Member of Technical Staff (Model Behavior Architect)

Полная занятостьОфис

Обязанности

  • 01Design, test, and optimize context strategies and system prompts that shape answer engine behavior across products, features, and use cases
  • 02Build automated and semi-automated evaluation pipelines that measure model quality, catch regressions, and scale across product surfaces
  • 03Partner with research and engineering to validate model behavior before and during rollouts, ensuring smooth transitions with no degradation
  • 04Identify inconsistencies and failure modes in model outputs through well-designed research projects — for both internal and production-facing systems
  • 05Work closely with design, product, and research teams to translate product goals into concrete model behavior requirements
  • 06Help engineers across teams build intuition for prompt design, context engineering, and evaluation best practices
  • 07Track the latest alignment, evaluation, and prompting techniques from industry and academia, and bring the best ideas back to the team

Требования

  • 01Experience designing evaluations, benchmarks, or metrics for AI systems
  • 02Strong written and verbal communication skills, particularly in explaining complex concepts to diverse stakeholders
  • 03Ability to manage multiple concurrent projects in a fast-moving environment
  • 04Strong experience with Perplexity or other frontier AI models in production settings
  • 05Demonstrated experience with Python — you'll prototype, debug, automate, and build systems at scale
  • 063+ years of experience working with LLMs in a product or research setting