RLHF Specialist

About the role

We are looking for an RLHF Specialist to design, implement, and optimise Reinforcement Learning from Human Feedback pipelines that enhance the safety, factual accuracy and human‑value alignment of large language models. The position is fully remote and works closely with machine‑learning engineers and global annotation teams.

Key responsibilities

• Generate high‑quality preference data by ranking model responses 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.
• Collaborate with ML engineers to analyse failure modes and identify data gaps.
• Develop and iterate annotation strategies for consistent preference scoring.
• Probe models for vulnerabilities, biases or hallucinations and document findings.
• Analyse edge cases where reward models behave unexpectedly and suggest data interventions.
• Translate complex RL concepts into repeatable tasks for junior reviewers.
• 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 safety.
• Strong proficiency in Python and deep‑learning frameworks (PyTorch, JAX or TensorFlow).
• Deep understanding of RL concepts such as PPO, trust‑region methods and reward hacking.
• Hands‑on experience fine‑tuning open‑source models (e.g., Llama 2/3, Mistral, Gemma) using LoRA/QLoRA.
• Experience with annotation platforms (LabelBox, Scale AI, Snorkel) and human‑in‑the‑loop workflows.
• Ability to diagnose collapsed RL policies and adjust hyper‑parameters or reward structures.
• Familiarity with Constitutional AI, self‑alignment techniques and open‑source alignment libraries.

Required skills

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