onsite
Member of Technical Staff - Cybersecurity Capabilities - Preference Model
Security Engineer
Join a cutting‑edge AI research team to design and implement high‑fidelity reinforcement‑learning environments, leveraging Python, distributed systems, and cloud infrastructure to accelerate real‑world ML research.
About the role
Key Responsibilities
- Design, develop, and maintain scalable RL training environments that model real‑world complexity.
- Implement robust reward functions and task suites to support diverse research objectives.
- Collaborate with ML researchers to integrate environments with large‑scale model training pipelines.
- Optimize performance and reliability using distributed computing frameworks and cloud services (e.g., AWS).
- Ensure data quality, versioning, and reproducibility across the environment ecosystem.
Requirements
- Strong proficiency in Python and experience building production‑grade ML/AI systems.
- Deep understanding of reinforcement learning concepts and practical implementation.
- Hands‑on experience with distributed systems, containerization, and cloud platforms such as AWS.
- Background in data engineering, including data pipelines, storage, and version control.
- Ability to work autonomously in a fast‑moving research environment and communicate effectively with cross‑functional teams.
Skills
pythonreinforcement learningmachine learningaws