RLHF Specialist – AI Model Alignment

About the role

We are looking for an RLHF Specialist to improve and align AI language models using Reinforcement Learning from Human Feedback. The role is fully remote and involves designing feedback pipelines that boost model safety, factual accuracy and alignment with human values.

Key responsibilities

• Generate high‑quality preference data by ranking model responses on helpfulness, honesty and harmlessness.
• Design multi‑turn prompts to stress‑test model reasoning and safety.
• Write chain‑of‑thought explanations to train reward models.
• Collaborate with ML engineers to analyse failure modes and close data gaps.
• Develop and iterate annotation strategies, ensuring consistency across a global team.
• Probe models for biases, hallucinations and vulnerabilities, documenting findings.
• Maintain a personal benchmark set and regularly re‑evaluate new model versions.
• Translate reinforcement‑learning concepts into repeatable tasks for junior annotators.

Required profile

• Minimum 2 years experience in data annotation, model evaluation, computational linguistics or trust‑and‑safety for AI/ML.
• Strong proficiency in Python and deep‑learning frameworks such as PyTorch, JAX or TensorFlow.
• Solid understanding of reinforcement‑learning algorithms (PPO, trust‑region methods) and their application to language generation.
• Hands‑on experience fine‑tuning open‑source models (e.g., Llama 2/3, Mistral, Gemma) using LoRA/QLoRA.
• Experience with annotation platforms like LabelBox, Scale AI or Snorkel.

Required skills

• Python
• PyTorch
• JAX
• TensorFlow
• Reinforcement Learning (PPO, Trust Regions)
• LoRA / QLoRA
• Llama 2, Llama 3, Mistral, Gemma
• LabelBox, Scale AI, Snorkel