poolside

Member of Engineering (Evaluations)

poolside
Apply
5 months ago
Remote, EMEAMid Level

Responsibilities

  • Design and implement infrastructure and tooling used by researchers and engineers.
  • Research and implement evaluations and benchmarks for base models and instruction-following models.
  • Collaborate with applied research and product teams to define metrics and evaluations for real-world software development skills.
  • Plan future work, discuss technical decisions, and communicate clearly with teammates.

Requirements

  • Experience with large language models and a strong understanding of their capabilities and limitations.
  • Strong engineering and programming background, ideally across multiple languages including Python.
  • Familiarity with the full software development lifecycle.
  • Linux experience and strong algorithmic skills.
  • Curiosity, critical thinking, good judgment, and willingness to question code-quality policies when appropriate.
  • Interest in using modern tools and continuously improving development practices.

Benefits

  • Fully remote work with flexible hours.
  • 37 days per year of vacation and holidays.
  • Health insurance allowance for the employee and dependents.
  • Company-provided equipment.
  • Wellbeing, learning, and home office allowances.
  • Frequent team get-togethers.
  • Remote-first team with monthly three-day in-person gatherings and longer offsites twice a year.

Tech Stack

Categories

poolside

About poolside

201-500 employees
Contact me