Senior Backend Engineer, ML Inference Platform

Shopee; Singapore; On-site; SGD 70,000 - 90,000; Full time

Job summary

A leading e-commerce platform in Singapore seeks an experienced engineer to optimize online inference services for deep learning models. The role requires a solid background in C++ programming, GPU optimization, and online inference techniques. The ideal candidate will engage in cutting-edge research, collaborating with various teams to ensure high-availability systems. This position promises an exciting opportunity to tackle significant technical challenges while contributing to impactful machine learning solutions.

Qualifications

• At least 2 years of relevant work experience.
• Proficient in lock optimization, memory pools, thread pools.
• Experience in online inference/serving.

Responsibilities

• Responsible for the R&D and optimization of online inference services.
• Conduct in-depth research into inference acceleration algorithms.
• Collaborate across the business pipeline to tune online service systems.

Skills

C++ programming

Deep Learning

GPU optimization

Multi-threading

Performance profiling

Team player

Education

Bachelor’s degree in Computer Science, Electronics, Automation, Software Engineering or related fields

Tools

TensorFlow + XLA

TensorRT

Triton

vLLM

Job description

A leading e-commerce platform in Singapore seeks an experienced engineer to optimize online inference services for deep learning models. The role requires a solid background in C++ programming, GPU optimization, and online inference techniques. The ideal candidate will engage in cutting-edge research, collaborating with various teams to ensure high-availability systems. This position promises an exciting opportunity to tackle significant technical challenges while contributing to impactful machine learning solutions.