Role Description
This is a full-time remote role for an AI Research Engineer specializing in Reinforcement Learning (RL). The AI Research Engineer will be responsible for developing and implementing state-of-the-art RL algorithms, collaborating on research projects, and integrating these algorithms into existing systems.
Qualifications
- Full-stack engineering, from data engineering to model architecture, RL and deployment.
- Experience with performance engineering and identifying bottlenecks in RL training.
- Experience with tuning reward functions, hyper-parameters and exploration strategies to solve complex tasks with deep RL.
- 8+ years of Python programming experience.
Nice to have
Advanced degree (MS or PhD) in Computer Science or related fieldExperience with k8s, docker, GPU Performance / systems engineering and model inference.