22 hours ago

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

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 22 hours agoStatus: Live

Job Summary

Build TikTok Shop’s next-generation AI search and shopping assistant, owning the end-to-end search stack from retrieval and ranking to multi-agent LLM engines, post-training infrastructure, and personalized memory. Design and ship ReAct-based agent workflows (DAG, RAG, MCP integration), improve multi-turn LLM query understanding, and optimize inference for relevance, latency, and rapid iteration through systems and serving enhancements. Collaborate to ship research into production at global scale.

Location: Seattle

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Design and ship ReAct-based AI search agents with planning, memory, and tool use, including DAG workflows and RAG pipelines for multi-turn shopping assistance and query understanding.
•Own the unified Agent Harness across Q&A cards, in-app chatbot, and visual search surfaces, integrating MCP tool-chain and delivering end-to-end A/B support.
•Improve LLM query understanding via multi-turn conversation, cross-lingual analysis, and reasoning chains; optimize answer generation for quality and latency (quantization, KV cache, continuous batching).
•Build personalized memory infrastructure for long-term user profiles and real-time memory (MemAgent), including near-real-time pipelines over large behavior sequences for low-latency serving.
•Collaborate on post-training pipelines (SFT, RL, distillation) and model-serving infrastructure (tensor parallelism, speculative decoding, PD separation) to accelerate experimentation and meet latency targets; bridge research to production with algorithm teams.

Key Requirements

•Bachelor’s or Master’s in Computer Science, Computer Engineering, or a related technical field.
•At least 3 years building large-scale distributed systems, search infrastructure, or low-latency online services.
•Proficiency in C++, Go, or Java (C++ preferred), with strong systems fundamentals (data structures, OS, networking, multithreading, Linux performance tuning).
•Strong grasp of LLM/agent technologies, including RAG, tool use, and multi-turn reasoning, with experience contributing to production AI systems.
•Excellent system design instincts; ability to architect and ship reliable, high-performance services with strong communication and ownership.

Experience:3+ yearsE-commerceSearchLLMDistributed systemsLow-latency systemsRecommendationPersonalization

Education:Bachelor's in Computer Science or Computer Engineering

Skills:System designCommunicationOwnership

Tech Stack:C++GoJavaLinuxReActRAGDAGMCPLLMQuantizationKV cacheContinuous batchingTensor parallelismSpeculative decodingPD separationVLLMTensorRT-LLMSGLangMemAgentSFT

Company Brief

TikTok

Short-form video platform that lets users create, share, and discover entertainment content through algorithmic recommendations. It also offers advertising and creator tools for brands, influencers, and businesses.

Industry: Digital Media

Company Size: Enterprise (1,001+ employees)

Growth: Scaleup

Headquarters: Singapore, Singapore

Founded: 2016

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

TikTok

22 hours ago

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

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 22 hours agoStatus: Live

Job Summary

Location: Seattle

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Design and ship ReAct-based AI search agents with planning, memory, and tool use, including DAG workflows and RAG pipelines for multi-turn shopping assistance and query understanding.
•Own the unified Agent Harness across Q&A cards, in-app chatbot, and visual search surfaces, integrating MCP tool-chain and delivering end-to-end A/B support.
•Improve LLM query understanding via multi-turn conversation, cross-lingual analysis, and reasoning chains; optimize answer generation for quality and latency (quantization, KV cache, continuous batching).
•Build personalized memory infrastructure for long-term user profiles and real-time memory (MemAgent), including near-real-time pipelines over large behavior sequences for low-latency serving.
•Collaborate on post-training pipelines (SFT, RL, distillation) and model-serving infrastructure (tensor parallelism, speculative decoding, PD separation) to accelerate experimentation and meet latency targets; bridge research to production with algorithm teams.

Key Requirements

•Bachelor’s or Master’s in Computer Science, Computer Engineering, or a related technical field.
•At least 3 years building large-scale distributed systems, search infrastructure, or low-latency online services.
•Proficiency in C++, Go, or Java (C++ preferred), with strong systems fundamentals (data structures, OS, networking, multithreading, Linux performance tuning).
•Strong grasp of LLM/agent technologies, including RAG, tool use, and multi-turn reasoning, with experience contributing to production AI systems.
•Excellent system design instincts; ability to architect and ship reliable, high-performance services with strong communication and ownership.

Experience:3+ yearsE-commerceSearchLLMDistributed systemsLow-latency systemsRecommendationPersonalization

Education:Bachelor's in Computer Science or Computer Engineering

Skills:System designCommunicationOwnership

Tech Stack:C++GoJavaLinuxReActRAGDAGMCPLLMQuantizationKV cacheContinuous batchingTensor parallelismSpeculative decodingPD separationVLLMTensorRT-LLMSGLangMemAgentSFT

Company Brief

TikTok

Industry: Digital Media

Company Size: Enterprise (1,001+ employees)

Growth: Scaleup

Headquarters: Singapore, Singapore

Founded: 2016

Website LinkedIn