Intern Engineer - AI Agent for Data
About The Position
Huawei Canada has an immediate internship opening for an Engineer. The Distributed Data Storage and Management Lab leads research in distributed data systems, aiming to develop next-generation cloud serverless products that encompass core infrastructure and databases. This lab addresses various data challenges, including cloud-native disaggregated databases, pay-by-query user models, and optimizing low-level data transfers via RDMA. Teams within this lab create advanced cloud serverless data infrastructure and implement cutting-edge networking technologies for Huawei's global AI infrastructure. Build enterprise data foundations using knowledge graphs, metadata systems, vector databases, and enterprise data sources. Develop retrieval and grounding systems that connect AI agents to authoritative business knowledge. Design and implement AI agents that interact with databases, APIs, documents, and enterprise tools. Build RAG and agent workflows for retrieval, reasoning, validation, and tool execution. Develop persistent memory and state management for long-running, multi-step agent workflows. Support auditability, traceability, workflow recovery, and cross-session continuity. Implement governance-aware controls for data access, tool invocation, and agent actions. Integrate with enterprise platforms, MCP-compatible tools, and multiple LLM providers.
Requirements
- Strong software engineering skills in Rust or Python, and backend system development.
- Familiarity with databases, APIs, cloud platforms, and distributed systems.
Nice To Haves
- Experience building AI agents, multi-agent systems, RAG pipelines, or workflow-based AI applications.
- Strong understanding of LLMs, retrieval systems, agent memory, orchestration, and tool use.
- Experience with vector databases, semantic search, knowledge graphs, embeddings, or metadata systems.
- Experience with LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, MCP, or similar frameworks.
- Experience with Neo4j, Elasticsearch/OpenSearch, Milvus, Weaviate, Pinecone, pgvector, or equivalent technologies.
- Experience building enterprise AI platforms, agentic workflow systems, or AI infrastructure products.
Responsibilities
- Build enterprise data foundations using knowledge graphs, metadata systems, vector databases, and enterprise data sources.
- Develop retrieval and grounding systems that connect AI agents to authoritative business knowledge.
- Design and implement AI agents that interact with databases, APIs, documents, and enterprise tools.
- Build RAG and agent workflows for retrieval, reasoning, validation, and tool execution.
- Develop persistent memory and state management for long-running, multi-step agent workflows.
- Support auditability, traceability, workflow recovery, and cross-session continuity.
- Implement governance-aware controls for data access, tool invocation, and agent actions.
- Integrate with enterprise platforms, MCP-compatible tools, and multiple LLM providers.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Intern
Education Level
No Education Listed
