Production AI/ML Engineer: LLMs, RAG & Infra

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

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

RSUs

Job summary

Amazon Data Services, Inc. is seeking an AI/ML Engineer to build, deploy, and operate ML/AI systems powering the agentic decision intelligence workflow. You will take models from notebooks to production, build the LLM integration layer, implement RAG pipelines, and establish evaluation frameworks for reliability.

This role is hands‑on with ML infrastructure, LLM applications, and production engineering, focusing on scalable, observable AI systems and end‑to‑end testing across the stack.

Qualifications

• 3+ years of non‑internship professional software development experience
• Bachelor's degree in Computer Science, Machine Learning, or related field (or equivalent experience)
• 2+ years deploying ML models to production environments
• Strong Python proficiency + experience with ML frameworks
• Experience with LLM APIs and prompt engineering
• Experience with cloud ML services
• Experience building data pipelines for ML (feature engineering, preprocessing, training data management)
• Solid software engineering fundamentals (testing, CI/CD, code review, production operations)

Responsibilities

• Build and maintain LLM-powered components: structured reasoning chains, narrative generation, recommendation rationale
• Implement and optimize prompt engineering pipelines with version control, A/B testing, and regression detection
• Build RAG (Retrieval-Augmented Generation) systems that ground LLM outputs in operational data, historical playbooks, and domain knowledge
• Build guardrails, validation layers, and output parsing for LLM responses. Optimize latency, cost, and quality trade-offs across LLM providers
• Deploy ML models to production. Implement model monitoring: drift detection, performance degradation alerts, automated retraining triggers
• Build A/B testing infrastructure for model experiments. Manage model versioning, rollback, and canary deployment. Ensure SLA compliance for inference latency and availability
• Own the operational health of AI/ML services: monitoring, alarming, on‑call, incident response, observability across the AI stack (prompt traces, latency histograms, token usage, error rates)
• Write comprehensive tests (unit, integration, end‑to‑end) for ML pipelines

Skills

Python

LLM APIs

Cloud ML services

Data pipelines

Production software

Education

Bachelor's degree in CS/ML or related

Tools

LangChain

LangGraph

CrewAI

Bedrock Agents

MLflow

SageMaker Pipelines

Step Functions

CDK

CloudFormation

Terraform

Feature stores

Job description

Amazon Data Services, Inc. is seeking an AI/ML Engineer to build, deploy, and operate ML/AI systems powering the agentic decision intelligence workflow. You will take models from notebooks to production, build the LLM integration layer, implement RAG pipelines, and establish evaluation frameworks for reliability.

This role is hands‑on with ML infrastructure, LLM applications, and production engineering, focusing on scalable, observable AI systems and end‑to‑end testing across the stack.