AWS AI-Native Developer

About the role

An AWS + AI-Native Developer builds applications with Artificial Intelligence embedded into their core architecture, workflows, and delivery lifecycle from day one. The focus is on model training, leveraging LLMs (Large Language Models), and constructing agentic workflows to accelerate production.

Responsibilities

• AWS: Hands-on with core services (EC2, EKS, DynamoDB, Lambda, API Gateway, S3).
• AWS Bedrock Agentic & LLM System Development: Build autonomous or semi-autonomous agents, orchestrate agent planning loops, manage tool calling, and implement memory modules.
• AI-Powered Coding: Use AI tools (e.g., Cursor, GitHub Copilot, Claude Code) to rapidly prototype and generate production-ready code.
• RAG Pipeline Construction: Develop Retrieval-Augmented Generation (RAG) systems using vector databases and semantic search.
• API/SDK Integration: Integrate LLMs (OpenAI, Anthropic) into applications using function calling, structured outputs, and workflow automation.
• Production Deployment: Take AI prototypes from Proof of Concept (PoC) to deployment using cloud platforms (AWS, GCP, Azure, Vercel).

Requirements

• Programming Languages: High proficiency in Python and TypeScript/JavaScript (React, Next.js, Node.js).
• AI Frameworks & Libraries: Experience with LangChain, LangGraph, LlamaIndex, or Semantic Kernel.
• Vector Databases: Familiarity with technologies such as Pinecone, Chroma, Milvus, or Vertex AI Vector Search.
• Development Tools: Hands-on experience with AI coding tools such as Cursor, Claude Code, and GitHub Copilot.
• Software Engineering Fundamentals: Strong understanding of Git, debugging, testing, API design, and clean code principles.

Preferred Qualifications

• Experience building custom GPTs, Claude Projects, or Multi-agent orchestration.
• Understanding of AI governance, security, and "human-in-the-loop" mechanisms.
• Experience with DevOps and MLOps tools (MLFlow, Kubeflow).

Key Characteristics

• AI-Centric Mindset: Solves problems by blending human judgment with machine intelligence, producing 3–10× more output.
• Adaptability: Learns new AI tools faster than the industry can create them.
• Product Focus: Focuses on building, optimizing, and deploying AI applications quickly rather than just researching models.