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 rationales for reward‑model training.
• Partner with engineers to analyse failure modes, identify data gaps, and propose targeted data interventions.
• Develop and maintain annotation strategies, ensuring consistency across a global reviewer team.
• Probe models for biases, hallucinations, and vulnerabilities, documenting findings for continuous improvement.
• 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 understanding of reinforcement‑learning concepts such as PPO, trust‑region methods, and reward hacking.
• Hands‑on experience fine‑tuning open‑source LLMs (e.g., Llama 2/3, Mistral, Gemma) with LoRA/QLoRA.
• Proven ability to translate complex RL concepts into repeatable annotation tasks.

Required skills

• Python programming
• Deep‑learning frameworks: PyTorch, JAX, TensorFlow
• Reinforcement Learning (PPO, trust‑region, reward hacking)
• LoRA / QLoRA fine‑tuning techniques
• Annotation tools: LabelBox, Scale AI, Snorkel
• Cloud platforms: AWS SageMaker, GCP Vertex AI