Software Engineer – Global E-Commerce Search Infrastructure (TikTok Shop)

What you'll do

• Develop ReAct-based search agents, RAG pipelines, and agent workflows for shopping assistance across TikTok Shop surfaces.
• Improve LLM query understanding and answer-generation quality and latency, including multi-turn and cross-lingual search.
• Build personalized memory and feature infrastructure, and contribute to model post-training and inference systems for production-scale deployment.

What they ask for

• Bachelor’s or Master’s in Computer Science, Computer Engineering, or a related technical field.
• At least 3 years of industry experience building large-scale distributed systems, search infrastructure, or low-latency online services.
• Proficiency in C++, Go, or Java; strong systems fundamentals, including data structures, OS, networking, multithreading, and Linux performance tuning.
• Solid grasp of LLM and agent technologies, including RAG, tool use, and multi-turn reasoning, with production AI systems experience.

Nice to have

• Experience with large-scale search, recommendation, advertising, personalization, or production agent/RAG systems.
• Familiarity with LLM inference optimization, post-training workflows, or tools such as vLLM, TensorRT-LLM, or SGLang; research publications at listed conferences.

Tools

C++, Go, Java, RAG, MCP, vLLM, TensorRT-LLM, SGLang

AI focus

Build AI search agents, LLM query-understanding and answer-generation systems, personalized memory, and supporting post-training and inference infrastructure.