Join our team to focus on refining and specializing large AI models for gaming applications. You'll work on techniques to make our models more responsive, creative, and aligned with gaming contexts.

Key Responsibilities:

• Develop advanced fine-tuning methodologies for large language models
• Implement reinforcement learning techniques to improve model behavior
• Create specialized training datasets for gaming-specific applications
• Research novel approaches to model alignment and instruction following

Qualifications:

• Advanced degree in AI, machine learning, or related technical field
• Experience with model fine-tuning and optimization techniques
• Strong understanding of reinforcement learning from human feedback
• Excellent programming skills and familiarity with deep learning frameworks

Preferred Qualifications:

• Background in gaming AI or interactive narrative systems
• Experience with advanced optimization algorithms
• Proven experience in transitioning research prototypes into production-ready solutions
• Knowledge of efficient inference techniques for large models