Middle Fullstack Developer (Python + React.js)

CML Team; United States; Remote; USD 90,000 - 130,000; Full time

Benefits offered by this job

Remote-friendly

Flexible schedule

Collaborative senior team

Job summary

CML Team is seeking a mid-level engineer to build end-to-end features for production AI applications. You will combine Python backend development with applied AI and data retrieval, contributing across the stack from services to user-facing functionality.

You'll work with an experienced team on AI-powered products such as chatbots, retrieval tools, and dashboards, with opportunities for growth in a remote-friendly, flexible environment.

Qualifications

• At least one year of hands-on Python experience, through commercial work or substantial personal projects.
• Experience building AI applications such as chatbots, retrieval tools, or simple agents.
• Understanding of RAG, LangChain or LangGraph, and vector databases.
• Solid knowledge of FastAPI and REST fundamentals.
• Familiarity with Git, SQL or NoSQL databases such as PostgreSQL or MongoDB, and Docker.

Responsibilities

• Develop and improve AI agent and retrieval-augmented generation features using frameworks such as LangChain or LangGraph.
• Build and maintain FastAPI services and REST endpoints.
• Integrate and tune vector stores such as pgvector, Qdrant, Pinecone, or Weaviate.
• Use AI APIs for function calling, embeddings, and prompt refinement.
• Write tests and improve basic monitoring and tracing for AI features.
• Package and deploy services with Docker, helping review metrics, logs, and performance.

Skills

Python

AI applications

REST APIs

LangChain/LangGraph

RAG

Tools

FastAPI

Docker

Git

PostgreSQL

MongoDB

Vector databases (pgvector, Qdrant, Pinecone, Weaviate)

Job description

Role overview

Build end-to-end features for production AI applications, combining Python backend development with applied AI and data retrieval. Example product areas include payment platforms, digital wallets, and AI dashboards. You’ll work with an experienced engineering team on services and user-facing functionality, with room to contribute across the stack.

Responsibilities

• Develop and improve AI agent and retrieval-augmented generation features using frameworks such as LangChain or LangGraph.
• Build and maintain FastAPI services and REST endpoints.
• Integrate and tune vector stores such as pgvector, Qdrant, Pinecone, or Weaviate.
• Use AI APIs for function calling, embeddings, and prompt refinement.
• Write tests and improve basic monitoring and tracing for AI features.
• Package and deploy services with Docker, helping review metrics, logs, and performance.

Requirements

• At least one year of hands-on Python experience, through commercial work or substantial personal projects.
• Experience building AI applications such as chatbots, retrieval tools, or simple agents.
• Understanding of RAG, LangChain or LangGraph, and vector databases.
• Solid knowledge of FastAPI and REST fundamentals.
• Familiarity with Git, SQL or NoSQL databases such as PostgreSQL or MongoDB, and Docker.

Nice to have

• Some React, Next.js, or TypeScript knowledge, or willingness to learn.
• Exposure to observability tools such as Prometheus, Grafana, or OpenTelemetry.
• Experience with CI/CD, cloud platforms, Redis, message queues, or caching.

Benefits and work setup

• Full-time, mid-level role in a remote-friendly, flexible environment.
• Opportunity to work on production AI products with a collaborative senior team.
• Competitive compensation and opportunities for growth.