Job Details

Member of Technical Staff - Reinforcement Learning (Infrastructure), AGI Autonomy

Job ID: 2902948 | Amazon.com Services LLC

The Amazon AGI SF Lab is focused on developing new foundational capabilities for enabling useful AI agents that can take actions in the digital and physical worlds. We're enabling practical AI that can actually do things for us and make our customers more productive, empowered, and fulfilled.

The lab is designed to empower AI researchers and engineers to make major breakthroughs with speed and focus toward this goal. Our philosophy combines the agility of a startup with the resources of Amazon. By keeping the team lean, we're able to maximize the amount of compute per person. Each team in the lab has the autonomy to move fast and the long-term commitment to pursue high-risk, high-payoff research.

In this role, you will work closely with research teams to design, build, and maintain systems for training and evaluating state-of-the-art agent models.

Key job responsibilities:

1. Develop cutting-edge training infrastructure to ensure large-scale reinforcement learning on LLMs runs highly efficient and robust.
2. Work across the entire technology stack, including low level ML system, job orchestration and data management.
3. Analyze, troubleshoot and profile complex ML systems, identify and address performance bottlenecks.
4. Work closely with researchers, conduct MLSys research to create new techniques, infrastructure, and tooling around emerging research capabilities.

BASIC QUALIFICATIONS

- PhD, or Master's degree and 3+ years of applied research experience
- Experience programming in Java, C++, Python or related language
- Experience with neural deep learning methods and machine learning
- Experience debugging ML systems

PREFERRED QUALIFICATIONS

- PhD in Computer Science, Machine Learning, or a related field, with a focus on ML System.
- Demonstrated experience in developing, implementing and debugging large scale ML systems.
- Experience with distributed systems, Megatron, vLLM, Ray, and working with GPUs.
- Experience with patents or publications at top-tier peer-reviewed conferences or journals.