GrepJob
Preference Model

Machine Learning Engineer, RL Environments - Internship

Preference Model
Apply
4 days ago
Toronto, Canada or San Francisco, CA, USAIntern

Responsibilities

  • Design and build RL environments for testing LLM reasoning.
  • Write clean, production-grade Python code.
  • Work with Docker to create reproducible environments.
  • Translate ML papers into concrete training tasks.

Requirements

  • Must be an undergrad or PhD student in CS, ML, math, physics, or a related field.
  • Strong Python programming skills are required.
  • Familiarity with LLMs and their strengths and weaknesses is essential.
  • Ability to work independently and iterate quickly based on feedback.

Benefits

  • Paid internship with potential for full-time return based on performance.
  • Ownership and autonomy in a fast-moving startup environment.
  • Opportunity to collaborate with top machine learning engineers.

Tech Stack

DockerPython

Categories

AI & MLData Science