Backend Engineer - Multi-Modal Content & Vector Systems

TikTok; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

TikTok's Recommendation Architecture Platform Team seeks a skilled engineer in Singapore to own and evolve the multi-modal content understanding pipeline. You will tackle challenges in service availability, throughput, and storage, while collaborating with the algorithm team on vector representations and large-scale retrieval.

Responsibilities include optimizing model inference, enhancing stability, and enabling platform-wide integration.

Qualifications

• Bachelor’s degree in CS or related field, with relevant experience.
• Strong programming skills in Python/C++, and solid coding style.
• Good communication and collaboration skills; eager to learn new technologies.

Responsibilities

• Lead service construction and iteration of the multi-modal content understanding pipeline; address availability, throughput, and storage bottlenecks.
• Collaborate with the algorithm team to apply video representation models and large-scale vector retrieval technologies.
• Abstract and enrich multi-modal vector computing components; optimize inference performance and system scalability.

Skills

Python

C++

Problem solving

Communication

Collaboration

Education

Bachelor’s Degree in Computer Science or related field

Tools

PyTorch

TensorFlow

CUDA

Job description

TikTok's Recommendation Architecture Platform Team seeks a skilled engineer in Singapore to own and evolve the multi-modal content understanding pipeline. You will tackle challenges in service availability, throughput, and storage, while collaborating with the algorithm team on vector representations and large-scale retrieval.

Responsibilities include optimizing model inference, enhancing stability, and enabling platform-wide integration.