Drive innovation in AI with APPIT Software Solutions as a Reinforcement Learning Engineer in Montreal, Canada. Design advanced RL systems that enhance autonomous decision-making and large language model alignment.
Join APPIT in a pivotal role that focuses on building adaptive AI agents through reinforcement learning. The position requires at least 5 years of ML experience, including 2 in reinforcement learning, wherein you will create and implement algorithms for enterprise optimization. Collaborating with research teams, you’ll translate theoretical advances into practical applications while enhancing training environments for RL agents.
Key Responsibilities:
• Create algorithms for enterprise optimization problems
• Build reward modeling pipelines for RLHF
• Develop simulation environments for agent evaluation
• Implement multi-agent RL systems for coordination
• Optimize training stability and sample efficiency
Requirements:
• 5+ years of ML, with 2+ in re...