Elevate adaptive AI capabilities with APPIT Software Solutions as a Reinforcement Learning Engineer in Montreal, Canada. Build cutting-edge systems for optimization and autonomous decision-making using advanced reinforcement learning techniques.
In this role, you will design and implement algorithms that tackle enterprise optimization challenges. With a focus on RLHF alignment for large language models, the position requires at least 5 years of machine learning experience, including 2 years in reinforcement learning. You will also develop simulation environments to train and evaluate RL agents while collaborating with research teams to bring RL innovations into production.
Key Responsibilities:
• Design reinforcement learning algorithms for optimization
• Build RLHF and reward modeling pipelines
• Develop environments for RL agent training
• Implement multi-agent systems for coordination tasks
• Optimize RL training stability and efficiency
Requirements:
• 5+...