RLHF Specialist

About the role

We are looking for an RLHF Specialist to help improve and align large language models using Reinforcement Learning from Human Feedback. The role is fully remote and focuses on building high‑quality feedback pipelines that boost model safety, factual accuracy, and alignment with human values.

Key responsibilities

• Generate preference data by ranking model responses on helpfulness, honesty, and harmlessness.
• Design multi‑turn prompts to stress‑test reasoning and safety.
• Write chain‑of‑thought explanations to train reward models.
• Collaborate with ML engineers to analyse failure modes and fill data gaps.
• Develop and iterate annotation strategies for consistent preference scoring.
• Probe models for biases, hallucinations, and vulnerabilities, documenting findings.
• Analyse edge cases where reward models behave unexpectedly and suggest data interventions.
• Translate complex RL concepts into repeatable tasks for junior annotators.
• Maintain a personal test set of prompts and re‑evaluate new model versions against historical benchmarks.

Required profile

• Minimum 2 years of experience in data annotation, model evaluation, computational linguistics, or AI trust & safety.
• Strong proficiency in Python and deep‑learning frameworks (PyTorch, JAX, TensorFlow).
• Deep 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) with LoRA/QLoRA.
• Experience with annotation platforms such as LabelBox, Scale AI, or Snorkel.

Required skills

• Python
• PyTorch
• JAX
• TensorFlow
• PPO (Proximal Policy Optimization)
• LoRA / QLoRA
• LabelBox
• Scale AI
• Snorkel
• AWS SageMaker
• GCP Vertex AI