Software Engineer Intern – LLM Agentic Engine

Job Description

Software Engineer Intern (Agentic AI Engine – Data Management platform) | TikTok

The Tone:
This is an internship opportunity at TikTok, a leading global company known for its short-form mobile video platform, with a mission to inspire creativity and bring joy. This role is within the cutting-edge Agentic Engine team, a division of the data platform team specifically focused on the adoption of Large Language Models (LLMs). As an intern, you will contribute to designing architectures and applying state-of-the-art AI technologies to real-world industry challenges within data development platforms, putting you at the forefront of AI innovation and shaping the future of intelligent systems.

The TL;DR
• Role: Internship
• Type: Full-time (12-week commitment)
• Location: In-person, San Jose, CA
• Pay: $45 hourly
• Team: Agentic Engine team, a division of the data platform team focused on LLM adoption.
• Mission: Design and implement state-of-the-art AI technologies and architectures for applying LLMs to industry challenges in data development platforms.
• Tech Stack: Spark, Flink, Hudi, Iceberg, DeltaLake, HDFS, Parquet, ORC, Java, C++, Scala, Hive, HBase, Kudu

What You’ll Actually Do
• Design: Create offline and real-time data architectures for large-scale recommendation systems.
• Implement: Build flexible, scalable, stable, and high-performance storage systems and computation models.
• Troubleshoot: Identify and resolve issues in production systems, designing necessary mechanisms and tools to ensure overall stability.
• Build: Construct industry-leading distributed systems such as offline and online storage, batch, and stream processing frameworks, providing reliable infrastructure for massive data and large-scale business systems.

The Must-Haves
• Background: Currently pursuing an Undergraduate or Master’s degree in Software Development, Computer Science, Computer Engineering, or a closely related technical discipline. Candidates must be able to commit to working for 12 weeks during Summer 2026.
• Experience: Required proficiency in common big data processing systems like Spark/Flink, demonstrated at the source code level, with a strong preference for candidates experienced in customizing or extending these systems. A deep understanding of the source code of at least one data lake technology, such as Hudi, Iceberg, or DeltaLake, is highly valuable, especially if coupled with practical implementation or customisation experience, and should be prominently showcased in your resume.
• Skills: Essential proficiency in programming languages such as Java, C++, and Scala, alongside strong coding abilities and the capability to troubleshoot effectively. Knowledge of HDFS principles is expected, and familiarity with columnar storage formats like Parquet/ORC is an additional advantage.
• Bonus: Prior experience in data warehousing modeling; experience with other big data systems/frameworks such as Hive, HBase, or Kudu. Additionally, advantageous qualities include a willingness to tackle challenging problems without clear solutions, a strong enthusiasm for learning new technologies, and prior experience in managing large-scale data, specifically in the petabyte range.