Agentic AI Scientist: Multi-Agent Orchestration & RL

Amazon Science; Bellevue (WA); On-site; USD 143,000 - 193,000; Full time

Job summary

Amazon Fulfillment Technologies (AFT) in Bellevue seeks an Applied Scientist to lead the development of agentic systems that support operational decision making and orchestration. You will build full agentic systems leveraging multi-agent orchestration, tool use, memory, and action execution.

You will train LLMs using rejection sampling, SFT, continual post-training, and Reinforcement Learning (RL); you will evaluate offline and online, mentor interns, and publish research papers to summarize

Qualifications

• PhD, or Master’s degree and 4+ years of CS, CE, ML or related field experience
• 3+ years of building models for business application experience
• Experience programming in Java, C++, Python or related language
• Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing

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.

Skills

Model building

Java/C++/Python

Algorithms & data structures

Numerical optimization

Data mining

Parallel & distributed computing

High-performance computing

Unix/Linux

Education

PhD or MS with 4+ years CS/CE/ML

Job description

Amazon Fulfillment Technologies (AFT) in Bellevue seeks an Applied Scientist to lead the development of agentic systems that support operational decision making and orchestration. You will build full agentic systems leveraging multi-agent orchestration, tool use, memory, and action execution.

You will train LLMs using rejection sampling, SFT, continual post-training, and Reinforcement Learning (RL); you will evaluate offline and online, mentor interns, and publish research papers to summarize