RLHF Specialist

About the role

We are looking for an RLHF Specialist to lead the design and execution of reinforcement‑learning‑from‑human‑feedback pipelines that improve the safety, factuality and alignment of large language models. The role is fully remote and collaborates closely with machine‑learning engineers and annotation teams.

Key responsibilities

• Generate high‑quality preference data by ranking model outputs 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.
• Work 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.
• Analyse edge cases where reward models behave unexpectedly and suggest data interventions.
• Create templated instruction sets for large annotation crews and translate RL concepts into repeatable tasks.
• Maintain a personal benchmark set and regularly re‑evaluate new model versions.

Required profile

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

Required skills

• Python
• PyTorch
• JAX
• TensorFlow
• LoRA / QLoRA
• LabelBox
• Scale AI
• Snorkel
• AWS SageMaker
• GCP Vertex AI