AI Engineer — Build, Deploy & Optimize Production AI
Posted Updated
Description
ai32 is seeking an AI Engineer to lead the AI layer of our product in Jakarta. You will design architectures, implement scalable AI systems, and work across product and engineering to deliver production-ready AI capabilities.
You will focus on improving answer quality, latency, reliability, and cost, while ensuring security and privacy through guardrails and robust execution practices. The role requires independent work and strong technical decision-making.
Design and Develop AI Solutions: Translate business requirements into AI architectures. Build and Deploy AI Capabilities: Collaborate to deploy production-ready AI solutions. Optimise AI Performance: Improve answer quality, retrieval accuracy, latency, reliability and costs. Implement AI Evaluations: Create tests and monitoring for AI quality and failures. Ensure AI Reliability and Security: Implement guardrails, access controls, privacy protections and reliable execution. Strong proficiency in Python and asynchronous services. Experience developing AI agents, workflows, tool calling, MCP, structured outputs, state, and memory. Solid understanding of Retrieval-Augmented Generation (RAG), embeddings, retrieval, reranking, and source grounding. Hands-on experience with Amazon Bedrock and AgentCore.Skills
Sign in to read and join the discussion.