RLHF Specialist

About the role

The RLHF Specialist will design and operate feedback pipelines that improve large language models through Reinforcement Learning from Human Feedback. Working remotely, you will collaborate with ML engineers to align model behavior with safety, factual accuracy, and 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 reasoning and safety, and write chain‑of‑thought explanations for reward‑model training.
• Partner with engineers to analyse failure modes, fill data gaps, and refine reinforcement‑learning outcomes.
• Develop and iterate annotation strategies, ensuring consistent scoring across a global team.
• Probe models for biases, hallucinations, or vulnerabilities and document findings.
• Maintain a personal benchmark set to monitor performance across model releases.

Required profile

• At least 2 years of experience in data annotation, model evaluation, computational linguistics, or AI trust & safety.
• Strong Python programming skills and familiarity with deep‑learning frameworks such as PyTorch, JAX, or TensorFlow.
• Solid understanding of reinforcement‑learning concepts (PPO, trust‑region methods, reward hacking) and their application to language generation.
• Hands‑on experience fine‑tuning open‑source models (e.g., Llama 2/3, Mistral, Gemma) using LoRA/QLoRA.

Required skills

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