Senior Software Engineer / Lead (ai/ml Platform)

Razer

Singapore, Singapore
On-site
Design and build ai/ml platform
High-throughput training and inference
Local and cloud gpu environments
Razer is seeking a Senior Software Engineer / Lead to design and build an AI/ML platform focused on high-throughput training and inference in GPU environments. The ideal candidate will have extensive experience in software engineering, machine learning infrastructure, and systems architecture, as well as strong leadership and collaboration skills

Job Summary

  • Join Razer on a global mission to revolutionize the way the world games, offering the opportunity to make an impact globally.
  • Design and build an AI/ML platform capable of high-throughput training and inference across local and cloud GPU environments.
  • Lead engineering initiatives, define platform architecture, and collaborate closely with ML and hardware teams.

Matching Summary

Match Score: 85

Razer is seeking a Senior Software Engineer / Lead to design and build an AI/ML platform focused on high-throughput training and inference in GPU environments. The ideal candidate will have extensive experience in software engineering, machine learning infrastructure, and systems architecture, as well as strong leadership and collaboration skills.

Skills & Requirements

Must-have

  • design and build AI/ML platform
  • high-throughput training and inference
  • local and cloud GPU environments
  • systems architecture
  • GPU acceleration
  • performance engineering
  • heterogeneous compute environments
  • high-performance inference stacks
  • model lifecycle management
  • GPU clusters on-prem and cloud
  • optimize GPU performance
  • deploy scalable GPU inference
  • distributed systems
  • container orchestration
  • GPU programming (CUDA or ROCm)

Nice-to-have

  • on-device or edge-accelerated inference
  • cloud-native GPU scheduling
  • model compression techniques
  • contributions to open-source AI infrastructure

Key Requirements

  • 8+ years of experience
  • Hands-on experience with local and cloud GPU environments
  • Deep knowledge of transformer-based models
  • Experience building high-availability distributed systems
  • Strong proficiency in Python
  • Proficiency in C++ or Go
  • Experience with deep learning frameworks
  • Experience with inference engines
  • Solid understanding of distributed systems
  • Solid understanding of parallel computing
  • Solid understanding of container orchestration
  • Solid understanding of GPU programming
  • Strong collaboration and communication skills
  • Ability to lead engineering efforts

Work Rights

Not specified

Tailored Resume

Cover Letter