Description

As an Applied Scientist in Amazon Fullfilment Technology, you will lead the development of agentic systems to assist with operational decision making and orchestration. You will work building full agentic systems leveraging multi-agent orchestration, tool use, memory, and action execution. You will train LLMs using a combination of rejection sampling approaches, SFT, continual post-training, and Reinforcement Learning (RL).

These systems are deployed to Amazon buildings, and you will also work on rigorous offline and online evaluations.

Your work will leverage the latest LLMs to develop capabilities for agentic reasoning, coding and analytics. You will also lead research projects to tackle unsolved problems, mentor interns, and author academic papers to summarize your findings for external publication.

Key job responsibilities
- Generating training and preference data for specific use cases (reasoning trajectories, tool traces)
- Reward modeling and policy optimization for LLMs: DPO, IPO, RLHF/RLAIF with PPO/GRPO, rejection sampling.
- Supervised fine-tuning on step-by-step trajectories and tool-use traces
- Verbal Reinforcement Learning and Continual Learning
- RL for LLMs, Offline RL and off-policy evaluation
- Agentic memory/state management; episodic and semantic memory; vector search; grounding with RAG.
- Evaluation: developing decision quality metrics, scaling LLM-based evaluations.


About the team
Amazon Fulfillment Technologies (AFT) powers Amazon’s global fulfillment network. We invent and deliver software, hardware, and data science solutions that orchestrate processes, robots, machines, and people. We harmonize the physical and virtual world so Amazon customers can get what they want, when they want it. Learn more about AFT: https://tinyurl.com/AFTOverview