Reinforcement Learning Engineer

A company is looking for a Reinforcement Learning Engineer.

Key Responsibilities

Generate and investigate research ideas to overcome obstacles in continuous learning for production

Collaborate with the OpenPipe team to validate research directions using real customer tasks

Engage in hands-on engineering tasks, including work on CUDA kernels and high-performance LLM tracing dashboards

Required Qualifications

Experience training LLMs to achieve state-of-the-art performance on specific tasks

Strong engineering background with a focus on rapid learning and shipping code

Demonstrated ability through impactful accomplishments in past projects or roles

Familiarity with reinforcement learning concepts and methodologies

Ability to work in a fast-paced, autonomous team environment