Staff Research Software Engineer: AI Inference & Efficiency

GOOGLE ASIA PACIFIC PTE. LTD.; Singapore; In loco; SGD 180.000 - 260.000; Tempo pieno

Descrizione del lavoro

Google Research Singapore seeks a technical leader to advance Generative AI models with a focus on inference efficiency and deployment at scale. You will help build a team from the ground up and collaborate with global AI groups to push frontier AI capabilities in Singapore.

Design and implement novel algorithms for high throughput and low latency, optimize low-level software and custom kernels, and publish research results to influence the AI research ecosystem.

Competenze

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

Mansioni

• Design and implement novel algorithms that optimize the inference stack for LLMs to maximize throughput and minimize latency.
• Develop and optimize low-level software; implement custom kernels for inference; improve latency, throughput, memory usage.
• Co-design algorithms with hardware accelerators; collaborate with hardware architects.
• Amplify impact through publications and scientific dissemination.

Conoscenze

Software development

Software architecture

ML infrastructure

Generative AI tools integration

LLM interfaces

Publications in AI

Formazione

Bachelor's degree or equivalent

PhD in ML/AI or related field (preferred)

Descrizione del lavoro

Google Research Singapore seeks a technical leader to advance Generative AI models with a focus on inference efficiency and deployment at scale. You will help build a team from the ground up and collaborate with global AI groups to push frontier AI capabilities in Singapore.

Design and implement novel algorithms for high throughput and low latency, optimize low-level software and custom kernels, and publish research results to influence the AI research ecosystem.