High-Performance Inference Platform Engineer

United States Digital Space LLC; Singapore; On-site; SGD 55,000 - 90,000; Full time

Job summary

United States Digital Space LLC is seeking talented individuals to join the Backend team in Singapore in 2027. The role focuses on building a high-performance, scalable enterprise inference system for large AI models, with emphasis on C/C++ development and Linux proficiency.

You will work on R&D for core modules, including inference engine scheduling, monitoring, canary releases, and performance tuning in concurrent environments, while collaborating across teams to drive robust technical

Qualifications

• Bachelor's or master's degree in computing or related field.
• Proficient in Linux basics and C/C++ programming.
• Solid knowledge of data structures and algorithms.
• Experience with multi-threaded concurrency and performance tuning.
• Experience in high-concurrency distributed services and latency optimization.
• Strong problem analysis, abstraction, and learning abilities.
• Excellent cross-team collaboration, communication, and documentation skills.

Responsibilities

• Architect and implement high-performance model inference services for large-parameter AI models.
• R&D and optimization of core inference framework modules (scheduling, monitoring, canary releases).
• Track latest inference technologies and promote standardization across the team.

Skills

C/C++ programming

Linux commands

Data structures & algorithms

Multi-threading

Performance tuning

Distributed services

Problem solving

Cross-team collaboration

Documentation

Education

Bachelor's/Master's degree in computing

Tools

Redis

RocksDB

BRPC

GRPC

GPUs knowledge

Job description

United States Digital Space LLC is seeking talented individuals to join the Backend team in Singapore in 2027. The role focuses on building a high-performance, scalable enterprise inference system for large AI models, with emphasis on C/C++ development and Linux proficiency.

You will work on R&D for core modules, including inference engine scheduling, monitoring, canary releases, and performance tuning in concurrent environments, while collaborating across teams to drive robust technical