English summary for screening — check the original posting before applying.
Join Nikkei's generative AI product team as an engineer focused on bringing LLM applications from prototype to production quality. You will design, implement, and operate RAG and agent-based workflows, addressing challenges like concurrency, throughput, cost, and SLOs.
Must-haves
- Experience designing and implementing LLM workflows and tools (e.g., LangGraph)
- Experience building and improving RAG systems (e.g., using Elasticsearch/OpenSearch)
- Experience designing production architectures for LLM applications, considering trade-offs and scalability
- Experience with quality assurance and evaluation for LLM outputs
- Experience integrating with execution environments (serverless/containers) and cloud services
- Proficiency in Python 3.10+
Nice-to-haves
- Experience with tools like Claude Code, Cursor, GitHub Copilot, Codex
- Experience with IaC tools like Terraform
- Experience with monitoring tools like Datadog