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. The role is fully remote and focuses on aligning 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.
• Collaborate with ML engineers to analyse failure modes, identify data gaps, and propose targeted data interventions.
• Develop and iterate annotation strategies, ensuring consistency across a global team of reviewers.
• Probe models for biases, hallucinations, or vulnerabilities and document findings for optimisation.
• Maintain a personal benchmark set, regularly re‑evaluating new model versions against historical performance.

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) using LoRA/QLoRA.
• Proficiency with annotation platforms (LabelBox, Scale AI, Snorkel) and human‑in‑the‑loop workflows.

Required skills

• Python programming
• PyTorch, TensorFlow, JAX
• Reinforcement Learning (PPO, trust‑region, reward hacking)
• LoRA / QLoRA fine‑tuning techniques
• LabelBox, Scale AI, Snorkel
• AWS SageMaker, GCP Vertex AI