Software Development Engineer, Dc Assistant Development

Amazon Amazon · Big Tech · Bellevue, WA · Software Development

Software Development Engineer role on the Data Center Gen AI team at AWS, focused on building generative AI solutions for data center operations. The role involves developing intelligent systems that optimize technician workflows, automate decision-making, and enhance operational efficiency using LLM integration, RAG, agent frameworks, and full-stack serverless technologies. The position aims to transform data center operations through AI/ML innovations and build platform primitives for other teams.

What you'd actually do

  1. Design and develop AI/ML platform features and solutions, contributing to systems that serve both data center operations and engineering teams
  2. Own end-to-end delivery of features and components, including AI integrations, deployment pipelines, and user-facing interfaces for non-ML experts
  3. Collaborate with senior engineers and cross-functional partners to integrate ML solutions into existing DC workflows, ensuring system quality and scalability
  4. Write clean, well-tested, and maintainable code while actively contributing to improvements in development processes, particularly for GenAI development and deployment
  5. Participate in technical design discussions and code reviews, bringing a customer-focused perspective to architectural decisions

Skills

Required

  • Generative AI / Agentic Systems
  • LLM integration
  • prompt engineering
  • RAG architectures
  • tool-calling patterns
  • agent frameworks (Strands, LangChain)
  • Full-Stack Serverless Engineering
  • AWS Lambda
  • API Gateway
  • CloudFront
  • DynamoDB/RDS
  • EventBridge
  • SQS
  • CDK Infrastructure-as-Code
  • Frontend & SDK Development
  • React
  • TypeScript
  • Cloudscape Design System
  • component library development
  • streaming interfaces (SSE)
  • Search & Knowledge Systems
  • OpenSearch/Elasticsearch
  • vector embeddings
  • hybrid retrieval
  • document processing pipelines
  • semantic chunking
  • ML & Data Engineering
  • SageMaker
  • time-series analysis
  • anomaly detection
  • classification models
  • feature engineering
  • ETL pipelines
  • Platform & DevOps
  • CI/CD pipeline development
  • progressive deployment
  • synthetic monitoring
  • observability (CloudWatch, X-Ray, OpenTelemetry)
  • writing clean, well-tested, and maintainable code
  • technical design discussions
  • code reviews

Nice to have

  • working knowledge of AI/ML technology application (LLMs, agents, RAG, Skills, ML models)
  • ownership of features and components end-to-end
  • pragmatic execution with creative problem-solving

What the JD emphasized

  • Generative AI / Agentic Systems
  • LLM integration
  • RAG architectures
  • tool-calling patterns
  • agent frameworks
  • AWS Lambda
  • API Gateway
  • CloudFront
  • DynamoDB/RDS
  • EventBridge
  • SQS
  • CDK Infrastructure-as-Code
  • React
  • TypeScript
  • Cloudscape Design System
  • component library development
  • streaming interfaces (SSE)
  • OpenSearch/Elasticsearch
  • vector embeddings
  • hybrid retrieval
  • document processing pipelines
  • semantic chunking
  • SageMaker
  • time-series analysis
  • anomaly detection
  • classification models
  • feature engineering
  • ETL pipelines
  • CI/CD pipeline development
  • progressive deployment
  • synthetic monitoring
  • observability (CloudWatch, X-Ray, OpenTelemetry)

Other signals

  • Generative AI / Agentic Systems
  • LLM integration
  • RAG architectures
  • tool-calling patterns
  • agent frameworks
  • AWS Lambda
  • API Gateway
  • CloudFront
  • DynamoDB/RDS
  • EventBridge
  • SQS
  • CDK Infrastructure-as-Code
  • React
  • TypeScript
  • Cloudscape Design System
  • component library development
  • streaming interfaces (SSE)
  • OpenSearch/Elasticsearch
  • vector embeddings
  • hybrid retrieval
  • document processing pipelines
  • semantic chunking
  • SageMaker
  • time-series analysis
  • anomaly detection
  • classification models
  • feature engineering
  • ETL pipelines
  • CI/CD pipeline development
  • progressive deployment
  • synthetic monitoring
  • observability (CloudWatch, X-Ray, OpenTelemetry)