RLHF Specialist (Remote)

About the role

The RLHF Specialist will design and operate reinforcement‑learning‑from‑human‑feedback pipelines to improve large language models. Working remotely, you will collaborate with ML engineers to enhance 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 that stress‑test model reasoning and safety.
• Write chain‑of‑thought explanations to train reward models.
• Collaborate with 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.
• Analyze edge cases where reward models behave unexpectedly and suggest data interventions.
• Create templated instruction sets for large annotation teams and train junior reviewers.
• Maintain a personal test set of prompts to monitor model performance over time.

Required profile

• Minimum 2 years experience in data annotation, model evaluation, computational linguistics, or AI trust and safety.
• Strong proficiency in Python and deep‑learning frameworks.
• Deep understanding of reinforcement‑learning concepts such as PPO, trust regions, and reward hacking.
• Hands‑on experience fine‑tuning open‑source LLMs (e.g., Llama 2/3, Mistral, Gemma) using LoRA/QLoRA.
• Experience with annotation platforms and human‑in‑the‑loop workflows.

Required skills

• Python
• PyTorch
• JAX
• TensorFlow
• Reinforcement Learning (PPO, Trust Regions, Reward Hacking)
• LoRA / QLoRA fine‑tuning
• LabelBox, Scale AI, Snorkel
• AWS SageMaker
• GCP Vertex AI