Compute System Arch Engineer, AI Infra - New College Grad 2027
Salary not listed • China, Shanghai • Full-time
Posted 2d ago
About the job
We are building reusable, reliable AI infrastructure for engineering teams, transforming technical documents, source code, and engineering data into accessible knowledge and enabling AI agents to perform complex engineering tasks. In this role, you will design and develop knowledge platforms, LLM service integrations, and agent execution frameworks, taking AI capabilities from prototypes to maintainable production systems for knowledge retrieval, test development, code review, and failure analysis.
Responsibilities
- Design and develop reusable AI platform components and services for model access, knowledge retrieval, tool calling, and workflow execution.
- Build data ingestion and processing pipelines for heterogeneous sources, supporting parsing, extraction, updates, versioning, and provenance.
- Develop retrieval-augmented generation (RAG) and knowledge infrastructure using vector search, keyword search, reranking, and structured knowledge.
- Develop agentic and multi-agent workflows with tool integration, context and state management, task scheduling, failure recovery, and human review.
- Build evaluation and observability systems using datasets, automated tests, and execution traces to measure and improve correctness, reliability, latency, and cost.
- Own platform deployment and maintenance, including access controls, data isolation, recovery mechanisms, and release processes.
- Collaborate with domain experts and application developers to translate engineering needs into platform capabilities.
Requirements
- Bachelor’s degree in Computer Science, Software Engineering, Electrical Engineering, or related field, or equivalent experience.
- Hands-on experience in software engineering, infrastructure, data platforms, machine learning engineering, or related areas.
- Strong Python programming skills and software engineering fundamentals.
- Familiarity with Linux, version control, automated testing, and CI/CD.
- Hands-on development and deployment experience in LLM application infrastructure, RAG systems, agent platforms, or model-serving systems.
- Understanding of LLM application mechanisms and limitations, including model APIs, embeddings, context management, tool calling, and evaluation.
- Experience with backend services, databases, and data processing, including concurrency, caching, task state management, failure recovery, and API design.
- Strong debugging, testing, and analytical skills.
- Ability to diagnose issues through logs, metrics, and experiments.
- Good communication, collaboration, and ownership skills.