Applied Scientist - Post-training
Core
Developing post-training methods to improve large language model alignment, reasoning, and reliability for deployed conversational systems.
Role type
Senior Applied Scientist (LLM Post-Training & Alignment)
Builds
Production-ready LLMs with improved human-centred behaviour, reasoning capabilities, and multilingual generalisation
Domain
Artificial Intelligence / Large Language Models / Machine Learning Research
Deliverable
production ML models
Required skills
LLM post-training, RLHF/RLAIF, instruction-tuning, preference-learning, continual learning, evaluation framework design, optimisation, published research, open-source contributions
Preferred skills
Experience with natural language interaction, autonomy in research, scaling research to production
Technologies
RLHF, RLAIF, continual learning frameworks, multilingual model architectures
Responsibilities
Develop post-training methods for alignment and reasoning; Advance instruction-tuning and preference-learning pipelines; Design evaluation frameworks for human-centred behaviour; Explore continual learning and multilingual generalisation; Publish research informing real-world deployment
Seniority
Senior, hands-on IC with research output