Applied Scientist, Agentic AI for Compliance & Trust

Amazon Web Services (AWS); Seattle (WA); On-site; USD 143,000 - 193,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Job summary

Amazon Development Center U.S., Inc. seeks an Applied Scientist to own and productionize the Natural Language Inference model powering AWS GRC decisions. You will fine-tune, calibrate thresholds, monitor drift, and shape agent-context systems for retrieval, grounding, and hallucination measurement.

You will design decomposition pipelines, improve evidence linking, and orchestrate evaluation and retraining cycles while ensuring privacy-safe data handling in an agile environment.

Qualifications

• 2+ years of building models for business application.
• 2+ years of programming in Java, C++, Python or related language.
• 2+ years of hands-on predictive modeling and large data analysis.

Responsibilities

• Own the production NLI model end-to-end: fine-tune, promote, calibrate thresholds, and monitor for drift.
• Design and implement framework decomposition pipelines translating controls into NLI hypotheses.
• Build and improve the evidence auto-linking system using ranking, embedding, and reranking techniques.

Skills

Java

C++

Python

Education

PhD in computer science, ML, or related field

Tools

LLMs

Job description

Amazon Development Center U.S., Inc. seeks an Applied Scientist to own and productionize the Natural Language Inference model powering AWS GRC decisions. You will fine-tune, calibrate thresholds, monitor drift, and shape agent-context systems for retrieval, grounding, and hallucination measurement.

You will design decomposition pipelines, improve evidence linking, and orchestrate evaluation and retraining cycles while ensuring privacy-safe data handling in an agile environment.