Staff Research Software Engineer — AI Inference

GOOGLE ASIA PACIFIC PTE. LTD.; Singapore; On-site; SGD 180,000 - 240,000; Full time

Job summary

Google Research Singapore is at the frontier of AI research, focusing on ultra-efficient Generative AI models and inference optimization. You will lead a small, agile team in a fast-paced environment, collaborating with other Google teams to push the boundaries of AI capabilities for billions of users.

The role involves pioneering algorithms, co-design with accelerators, and contributing to a strong publication record in top venues.

Qualifications

• Bachelor's degree or equivalent practical experience.
• 8 years of software development experience.
• 5 years of testing and launching software products, and 3 years in design/architecture.
• 5 years of experience with ML design and ML infrastructure (model deployment/evaluation, data processing, debugging, fine tuning).
• Experience integrating generative AI tools or LLM interfaces into workflows.

Responsibilities

• Design and implement novel algorithms to optimize the inference stack for LLMs with high throughput and low latency.
• Develop and optimize low-level software and custom kernels for inference across hardware and model architectures.
• Co-design algorithms leveraging hardware accelerators and collaborate with hardware architects.
• Amplify impact through publications and dissemination in the research ecosystem.

Skills

Software development

Algorithm design

Low-level optimization

ML systems

Hardware-software co-design

Education

Bachelor's degree or equivalent

8 years of software development experience

5 years testing and launching software products

3 years in software design and architecture

5 years ML design and ML infrastructure

Job description

Google Research Singapore is at the frontier of AI research, focusing on ultra-efficient Generative AI models and inference optimization. You will lead a small, agile team in a fast-paced environment, collaborating with other Google teams to push the boundaries of AI capabilities for billions of users.

The role involves pioneering algorithms, co-design with accelerators, and contributing to a strong publication record in top venues.