About the role
YTL AI Labs is seeking a Backend Platform Engineer to design and build reusable AI capabilities powering our AI-enabled products. The role emphasizes API design, system-level optimization, and turning cutting-edge AI workflows into developer-friendly infrastructure.
You will design services for RAG, memory APIs, agent orchestration, and prompt workflows, build libraries and SDKs, and collaborate with product engineers to drive performance and reliability.
Designing and maintaining services for RAG, memory APIs, agent orchestration, and prompt workflows Building APIs and SDKs that abstract away LLM provider specifics and enable easy integration Supporting AI Product Engineers and researchers to tune for performance, reliability, and usability Following production-grade practices with observability, test coverage, and documentation 3+ years of software engineering experience, with focus on backend systems or developer platforms. Proficiency in Python and experience with FastAPI or similar frameworks. Familiarity with LLM APIs (e.g., OpenAI, Anthropic), vector search (Milvus, Weaviate, pgvector), and RAG logic. Experience building internal libraries, services, or APIs used across teams.