Expert Backend Engineer (Machine Learning Server Parameter) - EGO team

Shopee; Singapore; On-site; SGD 120,000 - 170,000; Full time

Job summary

Shopee invites an experienced C++ engineer to join the EGO team, building high-performance distributed parameter server systems for large-scale recommendation, search and ads. You will optimize multi-threaded code and work with KV storage and NVMe-backed systems to support real-time inference and offline training.

Responsibilities include integrating PS into the ML platform and delivering robust, scalable software through strong debugging and profiling skills, collaboration, and rigorous code

Qualifications

• Bachelor’s degree or above in CS, Electronics, Automation, Software Eng., or related fields with at least 6 years of experience.
• Proficient in C++ with strong low-level skills; multi-threading, memory management, GDB, performance tuning, RPC.
• Experience with distributed PS and high-performance in-memory KV/storage systems is a plus.

Responsibilities

• Develop distributed Parameter Server (PS) systems for large-scale models in search, ads, and recommendations.
• Integrate PS system into one-stop ML platform to provide stable, high-performance services.

Skills

C++

Multithreading

Lock optimization

Memory pool

Thread pool

Template programming

GDB debugging

Performance tuning

RPC frameworks

Education

Bachelor’s degree

Tools

KV storage systems

NVMe-SSD

Distributed PS systems

Job description

About The Team

The EGO team is dedicated to building an industry-leading machine learning platform to effectively support the implementation of algorithms across various business domains such as recommendation, search, and advertising. It focuses on extreme optimization for CTR/CVR prediction in large-scale sparse parameter scenarios, ensuring maximum performance in e-commerce applications and delivering greater value to the company. The EGO platform covers the entire deep machine learning workflow — from sample organization and training to model building and publishing, and further to online model loading and inference services. It comes with a user-friendly Web UI and Restful API, providing an end-to-end, one-stop machine learning platform.

Job Description

• Develop distributed Parameter Server (PS) systems for large-scale sparse model training and inference platforms in the search, advertising, and recommendation domains. The system should support high-throughput parameter read/write and update operations, handle hundreds of billions of features and TB-level sparse models, enable online real-time learning, and meet algorithmic needs such as feature admission and expiration.
• Participate in the development of the one-stop machine learning platform, integrating the PS system into the platform to provide a user-friendly, stable, high-performance, and platform-level distributed parameter service system. Enhance the platform’s efficiency and usability, accelerating the model iteration process for algorithm teams.

Requirements

• Bachelor’s degree or above in Computer Science, Electronics, Automation, Software Engineering, or related fields, with at least 6 years of relevant experience.
• Proficient in C++ programming with strong low-level technical skills; adept at multi-threaded programming, lock optimization, memory pool, thread pool, template programming, GDB debugging, performance tuning, and RPC frameworks.
• Familiarity with distributed PS systems, distributed system backend optimization, high-performance in-memory KV systems, KV storage systems based on NVMe-SSD, and high-performance client-server architecture systems is a plus.
• Highly passionate about computer technology, proactive in learning, with a strong spirit of in-depth research and hands-on practice. Maintains high standards and strict requirements for delivered code; works with rigor and attention to detail.
• Strong team player with excellent continuous learning ability.