AI Integration Specialist

Role overview A fully remote engineering role dedicated to designing and integrating production-grade large language model solutions for client web products and internal AI workflows. The work spans leading model platforms including OpenAI, Anthropic Claude, DeepSeek, and HuggingFace, with a strong emphasis on reliable, real-world deployment.

Responsibilities - Design, build, and integrate LLM-powered features into client-facing web products and internal automation workflows. - Select and orchestrate models from providers such as OpenAI, Anthropic Claude, DeepSeek, and HuggingFace based on use-case fit. - Implement vector database integrations and retrieval-augmented generation pipelines for grounded, context-aware responses. - Develop in Python or TypeScript and Node.js, following clean code and review practices. - Build and consume REST APIs and webhooks, designing reliable asynchronous workflows. - Contribute to multi-agent architectures and continuous evaluation practices for generative AI systems.

Requirements - Indonesian citizen residing in Indonesia; this is a 100% full remote position. - Two or more years of hands-on software development experience with AI, LLMs, and vector databases. - Professional written and spoken English proficiency for collaboration with global client teams. - Proficiency in Python or TypeScript with Node.js. - Solid grasp of REST APIs, webhooks, and asynchronous workflow design.

Nice to have - Genuine enthusiasm for generative AI, agent-based systems, and ongoing model evaluation. - Experience shipping AI features to production at scale.