Description

You will build tools and systems to facilitate Reinforcement Learning from Human Feedback (RLHF) to improve Large Language Model (LLM) performance.

Responsibilities

• Build tools to facilitate human feedback and integrate it into model training processes.
• Evaluate LLM outputs and provide qualitative feedback to guide model improvement.
• Collaborate with data scientists and ML engineers to integrate feedback into learning workflows.
• Document processes and best practices for incorporating human feedback into LLM training.
• Experiment with new methods to enhance feedback collection and integration in RLHF tasks.

Required Skills

• 3+ years of professional Rust development experience.
• Strong understanding of systems programming, performance optimization, and concurrency.
• 3+ years of hands-on experience with Git and CI/CD pipelines.
• Experience with LLMs and machine learning concepts.
• Strong problem-solving skills for analyzing and optimizing RLHF tasks.
• Ability to evaluate and provide constructive feedback on AI/ML outputs.
• Any Graduate degree.

Preferred Skills

• Familiarity with reinforcement learning.
• Experience in human-computer interaction or user feedback systems.

Key Skills

Education

Any Graduate