Software Engineer Intern (CIS Knowledge Bank)

About the Role

The CIS Knowledge Bank team builds Prism and OneContext, the knowledge and context infrastructure that helps ByteDance business agents access reliable, fresh, and permission-aware enterprise context. The team works on Personal Profile, Personal Knowledge Bank, and Group Knowledge Bank. Their systems support Lark document ingestion, knowledge extraction, retrieval, permission enforcement, evaluation, and agent workflows for scenarios such as PMO weekly reports, business Q&A, and enterprise AI assistants. This internship offers students hands-on experience, industry exposure, and opportunities to apply their knowledge to real-world challenges.

Key Responsibilities

• Build and iterate backend services for Prism and OneContext, including knowledge ingestion, extraction, indexing, retrieval, and update workflows.
• Transform Lark documents, meeting notes, messages, and business context into structured Knowledge Bank topics with clear provenance and access control.
• Improve retrieval quality and evaluation loops for RAG and agent workflows, including recall quality, adoption metrics, feedback processing, and observability.
• Develop internal tools, CLI/MCP interfaces, and service APIs that help agents and users query, import, and maintain knowledge safely and efficiently.
• Collaborate with product managers and engineers to turn real business scenarios into reusable Knowledge Bank capabilities.

Requirements & Tech Stack

• Currently pursuing a Undergraduate in Computer Science, Computer Engineering, Software Engineering or a related technical discipline.
• Solid computer science fundamentals, including data structures, algorithms, operating systems, databases, and distributed systems basics.
• Proficient in at least one general-purpose programming language such as Go, Python, TypeScript, Java, or C++.
• Interested in building reliable backend systems for LLM applications, RAG, information retrieval, data pipelines, or agent platforms.
• Able to understand ambiguous product requirements, break down engineering problems, and communicate clearly with cross-functional partners.

Preferred Qualifications

• Experience building evaluation, monitoring, experimentation, or feedback-loop infrastructure for AI products.
• Experience with developer tools, CLI/MCP tools, workflow automation, or AI agent frameworks.
• Strong curiosity about enterprise AI and a practical mindset for turning messy real-world context into useful product capabilities.

Internship Availability: Please clearly state your availability in your resume, including your start and end dates.

Application Limit: Candidates may apply to a maximum of two positions across ByteDance and its affiliates globally.

Application Review: Applications are reviewed on a rolling basis.