Senior Mern Stack Engineer (GenAI & LLMOps Platform)

Experience: 4-5 Years

Job Type: Full-time

About Katonic: We are a young Australian generative AI startup headquartered in Sydney, Australia.

Senior MERN Stack Developer

integration

Key Responsibilities:

• Design and develop scalable web applications using the MERN stack (MongoDB, Express.js, React.js, Node.js).

• Integration & Orchestration:

  Act as the bridge between the UI and the backend/AI team; build the Node.js middleware that consumes existing Python/FastAPI microservices and serves data to the frontend.
• Build intuitive React interfaces for GenAI features, including real-time chat, prompt playgrounds, and dashboards.
• Implement real-time data handling using WebSockets/SSE to stream LLM tokens from the backend to the user.
• Collaborate with Backend and AI Engineers to define and consume API contracts (REST/gRPC) for model serving and RAG pipelines.
• Optimize front-end performance and state management (Redux/Context API) to handle complex JSON outputs from AI models.
• Write clean, maintainable code with unit and integration tests to ensure the "glue" between systems is robust.

Required Skills:

• 4-5 years of hands-on experience in full-stack development using Node.js and React.js.
• Strong proficiency in JavaScript, TypeScript, and modern ES6+ syntax.

• API Integration Mastery:

  Deep experience consuming complex RESTful APIs and Microservices; ability to work with existing backend architectures.
• Solid understanding of Generative AI concepts (LLMs, Embeddings, Context Windows) to effectively integrate them.
• Experience building real-time applications (Chatbots) using WebSockets or Socket.io.
• Proficiency with state management libraries (Redux, Zustand) and React Hooks.
• Familiarity with Docker and containerization basics.

Preferred Skills (Integration Focus):

• Microservices Integration:

  Proven experience integrating Node.js applications with Python-based backends (FastAPI, Flask, or Django).

• API Standards:

  Familiarity with

  OpenAPI/Swagger

  specifications to understand and test existing backend endpoints.

• Event-Driven Integration:

  Experience with message queues (RabbitMQ, Kafka, or Redis) to handle asynchronous AI task processing.

• AI Frameworks:

  Experience using

  LangChain

  or Vercel AI SDK to chain together existing backend models and tools.

• Vector Data Consumption:

  Ability to integrate and query Vector Databases (Pinecone, Weaviate) within the application layer.

• Basic Python Literacy:

  Ability to read/understand Python code to facilitate better collaboration with the backend team.

What We Offer:

• Opportunity to build the application layer for a cutting-edge GenAI & LLMOps ecosystem.
• Work with advanced LLMs, GPUs, embeddings, and multimodal AI technologies.
• Collaborative environment with engineering, AI/ML research, DevOps, and product teams.
• 100% work from home.

"Please apply only if you match the criteria.”

To apply, please fill out this form here:

Without completing the form, your application will not be considered complete.