RLHF Specialist

About the role

We are looking for an RLHF Specialist to help improve and align large language models using Reinforcement Learning from Human Feedback. The role is fully remote and focuses on building high‑quality preference datasets, designing reward models, and collaborating with engineers to enhance model safety, factual accuracy, and alignment with human values.

Key responsibilities

• Generate and rank preference data by comparing 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.
• Work with ML engineers to analyse failure modes and identify data gaps.
• Develop and iterate annotation strategies for consistent preference scoring across a global team.
• Probe models for vulnerabilities, biases, or hallucinations and document findings.
• Maintain a personal benchmark set to monitor model performance over time.

Required profile

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

Required skills

• Python programming
• Deep‑learning frameworks: PyTorch, JAX, TensorFlow
• LoRA / QLoRA fine‑tuning techniques
• Annotation tools: LabelBox, Scale AI, Snorkel
• Cloud platforms: AWS SageMaker, GCP Vertex AI