AI Alignment Engineer: RLHF & Reward Modeling

Odixcity Consulting

Full-time IT & Technology
Apply Now
Location
Remote, Remote, South-Africa
Posted
June 27, 2026

Job Description

Odixcity Consulting is hiring an RLHF Specialist to enhance and align AI models using reinforcement learning methodologies. This role involves designing feedback pipelines, generating high-quality preference data, and collaborating with machine learning engineers. Candidates should have at least 2 years of experience in relevant fields, strong Python skills, and familiarity with deep learning frameworks. The position is remote, allowing for global collaboration on cutting-edge AI technologies.
#J-18808-Ljbffr