ML Systems Engineer: TPU Training & Inference Optimizer

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

Job summary

Google in Singapore is seeking an ML software engineer to lead onboarding and optimization for training and serving on the latest TPU-based stacks. You will contribute to the AI Engine and infrastructure supporting ML training/inference workloads on Cloud GPUs/TPUs.

We value experience in firmware, kernel development, and scalable server design. You’ll collaborate across teams to advance Google’s ML capabilities and distributed systems at scale.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 2 years of experience with software development in one or more programming languages, or 1 year of experience with an advanced degree.
• 1 year of experience leading ML design and optimizing ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning).
• 1 year of experience with training (e.g., Megatron-LM, DeepSpeed) and inference techniques (e.g., TensorRT-LLM, vLLM, SGLang).

Responsibilities

• Act as ML software engineer leading the onboarding for stable stack, and optimization for training and serving solutions on the latest TPU NPIs.
• Possess extensive technical knowledge of firmware design, kernel development, and server system integration, with the ability to influence the ecosystem.
• Triage product or system issues and debug/track/resolve by analyzing the sources of issues and the impact on hardware, network, or service operations and quality.
• Participate in, or lead design reviews with peers and stakeholders to decide amongst available technologies.
• Lead the server software design, development, and implementation on a scalable and high-quality Cloud Server Program, overseeing the project from conception to launch.

Skills

ML design

ML training

Inference techniques

Education

Bachelor's degree

Tools

Megatron-LM

DeepSpeed

TensorRT-LLM

vLLM

SGLang

Job description

Google in Singapore is seeking an ML software engineer to lead onboarding and optimization for training and serving on the latest TPU-based stacks. You will contribute to the AI Engine and infrastructure supporting ML training/inference workloads on Cloud GPUs/TPUs.

We value experience in firmware, kernel development, and scalable server design. You’ll collaborate across teams to advance Google’s ML capabilities and distributed systems at scale.