Production AI/ML Engineer: LLMs, RAG & Analytics

Amazon; Seattle (WA); On-site; USD 144,000 - 194,000; Full time

Benefits offered by this job

Health benefits

401(k) matching

Paid time off

Parental leave

Job summary

Amazon Global Data Center Ops Central Insight and Analytics Team seeks an AI/ML Engineer to bring ML/AI models from notebooks to production. You will integrate LLMs, build RAG systems grounded in operational data, and implement robust validation, latency optimizations, and monitoring across the stack.

You will write production-grade code, deploy models, and own end-to-end tests, with a focus on reliability and observability in a large-scale data platform environment.

Qualifications

• 3+ years of professional software development experience.
• Bachelor's degree in Computer Science, ML, or related field.
• 2+ years deploying ML models to production environments.
• Strong Python proficiency and ML framework experience.
• Experience with LLM APIs and cloud ML services.
• Experience building data pipelines for ML.

Responsibilities

• Build and maintain LLM-powered components and RAG pipelines.
• Implement and optimize prompt engineering workflows and tests.
• Deploy ML models to production with monitoring and retraining triggers.
• Own observability: traces, latency, token usage, and SLA compliance.
• Write comprehensive unit to end‑to‑end tests for ML pipelines.

Skills

Python

ML frameworks

LLM APIs

Cloud ML services

Data pipelines

CI/CD

Testing

Education

Bachelor's in CS/ML or related field

Tools

LangChain

Bedrock Agents

LangGraph

CrewAI

SageMaker Pipelines

MLflow

Terraform

CDK

Job description

Amazon Global Data Center Ops Central Insight and Analytics Team seeks an AI/ML Engineer to bring ML/AI models from notebooks to production. You will integrate LLMs, build RAG systems grounded in operational data, and implement robust validation, latency optimizations, and monitoring across the stack.

You will write production-grade code, deploy models, and own end-to-end tests, with a focus on reliability and observability in a large-scale data platform environment.