Senior AI Mobile-App Engineer (React Native & LLM)

Nityo Infotech Indonesia; Jakarta Pusat; On-site; IDR 360,000,000 - 720,000,000; Full time

Job summary

Nityo Infotech Indonesia seeks an AI-focused architect to design and deploy production AI solutions with modern frontend and robust backend services. You will lead LLM integration, RAG pipelines, and scalable API design in a cloud-native environment.

Ideal candidates have hands-on AI application development experience, strong DevOps skills, and a proactive, ownership-driven approach to delivering secure, production-grade software across teams.

Qualifications

• Direct hands-on experience building AI applications with LLM integration and RAG pipelines.
• Deep experience with backend integration, API design and cloud-native backend development (Python preferred).
• Proven DevOps skills: Docker, Kubernetes, CI/CD, and cloud platforms (GCP preferred).
• Familiarity with AI orchestration frameworks and vector databases.
• Self-directed with strong problem-solving and stakeholder communication.

Responsibilities

• End-to-End AI Integration: Architect, build, and deploy production-grade AI solutions with React Native frontend and cloud-native backend services.
• LLM & Agent Workflow Engineering: Implement LLM capabilities using Gemini, OpenAI, Claude and RAG workflows.
• Orchestration & Backend Development: Design scalable APIs, orchestration frameworks, vector DBs, and knowledge retrieval systems.
• Cloud-Native Deployment: Containerize services with Docker/Kubernetes and manage CI/CD pipelines on cloud infrastructure with monitoring.
• Autonomous Execution: Own technical deliverables and translate product concepts into production-ready apps.

Skills

AI Architecture

Backend APIs

DevOps & Cloud

AI Tooling

Ownership & Communication

Tools

LangChain

LangGraph

n8n

Copilot Studio

Vertex AI

Job description

• End-to-End AI Integration: Architect, build, and deploy production-grade AI solutions, combining modern React Native frontends with robust, cloud-native backend services.
• LLM & Agent Workflow Engineering: Implement state-of-the-art LLM capabilities (Gemini, OpenAI, Claude) using RAG architectures, prompt engineering, and intelligent chatbot integrations.
• Orchestration & Backend Development: Design scalable APIs and integrate orchestration frameworks, vector databases, and knowledge retrieval systems to power AI-driven applications.
• Cloud-Native Deployment: Containerize services using Docker/Kubernetes and manage deployment pipelines on cloud infrastructure (GCP preferred) with CI/CD, proactive monitoring, and production support.
• Autonomous Execution: Take full ownership of technical deliverables—converting high-level product concepts into performant, secure, and production-ready applications.

Requirements

• AI Application Architecture: Direct hands-on experience building AI applications, including direct LLM integration (Gemini, Claude, OpenAI), RAG pipeline development, and prompt optimization.
• Backend & API Systems: Deep experience with backend integration, API design, and cloud-native backend development (Python proficiency highly valued).
• DevOps & Cloud Infrastructure: Proven experience with Docker, Kubernetes (or equivalent container orchestration), CI/CD pipelines, and cloud platforms (GCP preferred, AWS or Azure accepted).
• AI Tooling (Preferred): Familiarity with AI orchestration frameworks (LangChain, LangGraph, n8n, Copilot Studio, Vertex AI) and vector databases.
• Professional Attributes: Self-directed operator with strong problem-solving skills, ownership mindset, and clear stakeholder communication capabilities.