AI Engineer
Summary
Builds LLM-powered applications in Jakarta: RAG pipelines (document processing, embeddings, retrieval), AI agents with tool/function calling, and REST APIs. Experiments with models and prompts, then deploys and optimizes services in Linux/Docker. Core stack: Python, LLMs/embeddings, vector databases like Milvus, Weaviate, Chroma.
Job Description:
Develop and integrate LLM-powered applications and AI services.
Build and improve RAG pipelines, including document processing, embeddings, retrieval, and response generation.
Integrate and work with multiple LLMs and AI models to support different application requirements.
Experiment with model selection, prompt engineering, and retrieval strategies to improve response quality, latency, and cost efficiency.
Develop AI Agents and workflows that integrate tools, function calling, APIs, and external services.
Develop and maintain AI services and REST APIs.
Deploy and maintain AI applications in Linux and Docker environments.
Evaluate model performance, response quality, and system reliability.
Troubleshoot and optimize AI applications and collaborate with software engineers to deliver production-ready solutions.
Qualifications:
Bachelor's degree in Computer Science, Informatics, Artificial Intelligence, or a related field.
Proficient in Python and familiar with developing AI/ML applications.
Understanding of LLMs, embeddings, RAG, and prompt engineering.
Familiar with integrating multiple AI models through APIs or local inference services.
Understanding of AI Agents, tool calling, and multi-step workflows.
Familiar with AI application frameworks and vector databases such as Milvus, Weaviate, Chroma, or similar technologies.
Basic understanding of REST APIs, databases, Docker, and Linux.
Strong problem-solving and troubleshooting skills.
Willing to learn and adapt to evolving AI technologies.