RLHF Specialist

About the role

We are looking for an RLHF Specialist to design, implement, and optimize reinforcement‑learning‑from‑human‑feedback pipelines that improve AI model performance, safety, and alignment with human values. This fully remote position works closely with machine‑learning engineers to generate high‑quality preference data and refine reward models.

Key responsibilities

• Generate and rank preference data by comparing model responses for 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 identify data gaps.
• Develop and iterate annotation strategies, ensuring consistency across a global team.
• Probe models for biases, hallucinations, and vulnerabilities, documenting findings.
• Analyze edge cases where reward models behave unexpectedly and suggest data interventions.
• Translate reinforcement‑learning concepts into repeatable tasks for junior annotators.
• Maintain a personal test set of prompts to monitor model performance over time.

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).
• Solid understanding of reinforcement‑learning algorithms (e.g., PPO, trust‑region methods) and their application to language models.
• Hands‑on experience fine‑tuning open‑source models (Llama 2/3, Mistral, Gemma) using LoRA/QLoRA.
• Experience with annotation platforms such as LabelBox, Scale AI, or Snorkel.
• Familiarity with cloud ML services (AWS SageMaker, GCP Vertex AI).

Required skills

• Python
• PyTorch
• JAX
• TensorFlow
• LoRA / QLoRA
• Llama 2, Llama 3
• Mistral
• Gemma
• LabelBox
• Scale AI
• Snorkel
• AWS SageMaker
• GCP Vertex AI