Staff Research Software Engineer

• Design and implement novel algorithms that optimize the inference stack for LLMs to ensure the highest througput and lowest latency for billions of users including sampling techniques, speculative decoding advancements, model compression, knowledge distillation and quantization strategies.
• Work on development and optimization of the low-level software that runs AI models efficiently. Implement and optimize custom kernels for inference, focusing on improving latency, throughput, and memory usage, across different hardware and model architectures.
• Co-design algorithms that exploit the unique architectectural advantages of custom hardware and accelerators. Collaborate with hardware architects on next-generation systems and use a deep understanding of both model architecture and hardware to inform algorithm selection.
• Amplify impact and influence the research ecosystem through publications and scientific dissemination.

Minimum qualifications:

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience testing, and launching software products, and 3 years of experience with software design and architecture.
• 5 years of experience with one or more of the following: Speech/audio (e.g., technology duplicating and responding to the human voice), reinforcement learning (e.g., sequential decision making), ML infrastructure, or specialization in another ML field.
• 5 years of experience with ML design and ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning).
• Experience integrating generative AI tools or LLM interfaces into workflows.

Preferred qualifications:

• PhD in Machine Learning, AI, Computer Science, Statistics, Applied Mathematics, Data Science, or a related technical field.
• Experience in a university or industry labs, with primary emphasis on AI research.
• Deep understanding of transformer architecture internals.
• Deep understanding of Machine Learning (ML) systems, distributed systems, compilers, or performance engineering. Experience in high-performance computing, or AI inference optimization and hands-on experience with low-level compute frameworks.
• Strong publication record in top AI venues.

Google Research Singapore is the very latest addition to the Google Research presence around the globe. This is an incredible opportunity to be advancing the frontier of AI capabilities in Singapore. The team delivers research on algorithmic efficiency, and inference acceleration, directly impacting how next-generation AI models will be deployed to billions of people.

In this role, you will sit at the heart of advancing fundamental capabilities of Artificial Intelligence (AI) to drive significant benefits to humanity. You will have the chance to help build a team from the ground up. You will be pioneering AI research in Singapore, focusing on enabling the most performant, ultra-efficient and capable Generative AI Models. You will be making pioneering breakthroughs towards Computational Efficiency for serving and deployment of large-scale Generative AI Models (e.g., Large Language Models (LLMs), Diffusion Models, Generative Videos). You will be a technical leader of a small and agile team, in an extremely fast-paced environment in close collaboration with other teams at Google.

Google will be prioritizing applicants who have a current right to work in Singapore, and do not require Google's sponsorship of a visa.

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience testing, and launching software products, and 3 years of experience with software design and architecture.
• 5 years of experience with one or more of the following: Speech/audio (e.g., technology duplicating and responding to the human voice), reinforcement learning (e.g., sequential decision making), ML infrastructure, or specialization in another ML field.
• 5 years of experience with ML design and ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning).
• Experience integrating generative AI tools or LLM interfaces into workflows.