AI Software Engineer – Full Stack

About the role

ChenMed is building an AI Agent and autonomous solutions team to transform senior care. As an AI Software Engineer you will design, develop, and ship AI‑powered backend services that support our care delivery model, working in a fast‑paced, startup‑like environment.

Key responsibilities

• Design and deploy AI application back‑ends using FastAPI (Python) or Node.js/Express (TypeScript).
• Containerize services with Docker and manage cloud deployments on AWS, Azure, or GCP.
• Build Retrieval‑Augmented Generation (RAG) pipelines using vector stores such as Pinecone, Chroma, or pgvector.
• Integrate large language model APIs (OpenAI, Anthropic), configure parameters, and orchestrate multi‑step reasoning with frameworks like LangGraph.
• Own the full software lifecycle in an Agile/Scrum setting, from inception to production support.
• Coordinate project schedules, design criteria, and deliver documentation to stakeholders.

Required profile

• Proven experience building AI back‑ends with FastAPI or Node.js/Express.
• Hands‑on expertise with Docker and cloud platforms (AWS, Azure, GCP).
• Familiarity with RAG pipelines, vector databases, and LLM integration.
• Ability to work autonomously, manage ambiguous requirements, and communicate clearly with cross‑functional teams.

Required skills

• Python, FastAPI
• TypeScript, Node.js, Express
• Docker
• AWS, Azure, GCP
• Pinecone, Chroma, pgvector
• OpenAI API, Anthropic API
• LangGraph or similar orchestration tools
• Atlassian suite (Bitbucket, Jira, Confluence)
• Microsoft Office Suite
• Agile/Scrum methodologies