Applied AI / Full-Stack AI Engineer (Mandarin / English Speaker)

HITHINK TECHNOLOGY INDONESIA; Jakarta Utara; On-site; IDR 180,000,000 - 300,000,000; Full time

Job summary

HITHINK TECHNOLOGY INDONESIA in Jakarta is seeking a Middle Applied AI / Fullstack AI Engineer (English/Chinese Speaker). You will build and deploy AI-powered applications, LLM features, and intelligent agent workflows, combining AI/LLM engineering with full-stack development.

You will work with Product, Design, and Operations to turn business needs into practical AI solutions, focusing on scalability, security, and cost efficiency in a fast-paced tech environment.

Qualifications

• Bachelor's degree in Computer science, Engineering, or a related field.
• 2-5 years of relevant AI/Full-Stack experience is preferred.
• Fluent bilingual in Mandarin or English (Listening/Speaking/Reading/Writing).

Responsibilities

• Build and deploy LLM/Generative AI features from prompt design to monitoring.
• Design and implement RAG systems with embeddings and vector search.
• Develop AI Agent workflows including tool calling and state management.
• Develop and maintain full-stack web applications for AI-powered products.
• Build scalable backend services and APIs using Node.js/TypeScript or Python.
• Integrate LLM APIs and external services, ensure security and observability.
• Collaborate with Product, Design, and Operations teams to deliver AI solutions.

Skills

AI engineering

Full-stack development

Backend engineering

LLM APIs

React

Next.js

Python

Node.js

TypeScript

Cloud platforms

Education

Bachelor's degree in computer science or related field

Tools

Node.js

TypeScript

Python

React

Next.js

OpenAI API

LangChain

Pinecone

Job description

Join our team at HITHINK TECHNOLOGY INDONESIA as Middle Applied AI / Fullstack AI Engineer (English/Chinese Speaker). This is a full-time position based in South Jakarta, Jakarta, offering you the opportunity to develop your skills and gain valuable experience in a dynamic, fast-paced technology environment.
We are looking for a Middle Applied AI / Full-Stack AI Engineer to build and deploy AI-powered applications, LLM features, and intelligent agent workflows.

You will combine AI/LLM engineering with full-stack development, taking AI features from concept to production while ensuring scalability, reliability, security, and cost efficiency. You will work closely with Product, Design, and Operations teams to turn business needs into practical AI solutions.

Key responsibilities

Build and deploy LLM/Generative AI features from prompt design, orchestration, backend integration, release, and monitoring.

Design and implement RAG systems, including embeddings, chunking, retrieval, reranking, citations, caching, and fallback mechanisms.

Develop AI Agent workflows including tool calling, state management, task automation, retries, guardrails, and fallback models.

Develop and maintain full-stack web applications supporting AI-powered products.

Build scalable backend services and APIs using Node.js/TypeScript, Python, or similar technologies.

Integrate LLM APIs, third-party APIs, databases, and external services.

Implement AI evaluation, regression testing, logging, monitoring, and observability to maintain AI quality and reliability.

Optimize AI/application performance, latency, scalability, and cost through caching, batching, context optimization, and model routing.

Apply security best practices including prompt-injection protection, PII handling, rate limiting, and abuse prevention.

Collaborate with Product, Design, and Operations teams to develop AI solutions that improve user experience and operational efficiency.

Requirements

Bachelor's degree in Computer science, Engineering, or a related field.

2-5 years of experience in AI Engineering, Full-Stack Development, Backend Engineering, or related roles.

Fluent bilingual communication (Listening/Speaking/Reading/Writing) in Mandarin or English.

Strong proficiency in Node.js/TypeScript or Python.

Experience with modern frontend frameworks such as React, Next.js, or similar.

Hands-on experience integrating LLM/Generative AI APIs such as OpenAI, Claude, Gemini, or similar.

Practical experience building AI Agents, agentic workflows, or AI-powered automation.

Strong understanding of RAG, embeddings, vector search, tokens, LLM cost, context management, and hallucination mitigation.

Experience with REST APIs, SQL/NoSQL databases, caching, queues, and third-party integrations.

Familiarity with AWS, GCP, Azure, or similar cloud platforms.

Strong software engineering practices including testing, debugging, logging, monitoring, documentation, and version control.

Strong problem-solving skills and ability to work independently in a fast-paced environment.

Nice to Have

Experience with LangChain, LlamaIndex, or custom AI orchestration.

Experience with vector databases such as pgvector, Pinecone, Qdrant, or Weaviate.

Experience with n8n, Zapier, or other workflow automation tools.

Familiarity with MLOps/LLMOps and observability tools such as OpenTelemetry, Prometheus/Grafana, or Sentry.

Understanding of microservices architecture.

Experience with STT/TTS or audio AI pipelines.

Experience building AI products for e-commerce, procurement, recruitment, or business workflow platforms.

Previous experience in a startup or fast-paced product environment.

Your application will include the following questions:

• What's your expected monthly basic salary?
• How many years' experience do you have as an Artificial Intelligence Engineer?
• Which of the following types of qualifications do you have?
• Which of the following languages are you fluent in?
• How many years of experience do you have in the IT Services Industry?