6 hours ago
Singapore, SingaporeStaff+
Responsibilities
- Design and implement algorithms that improve LLM inference throughput and latency, including sampling, speculative decoding, model compression, knowledge distillation, and quantization strategies.
- Develop and optimize low-level software and custom kernels for efficient AI model inference across hardware and model architectures.
- Co-design algorithms with hardware architects for custom hardware and accelerators.
- Lead technical work on a small team and collaborate closely with other Google teams.
- Publish and disseminate research findings through the broader scientific and research ecosystem.
Requirements
- Bachelor’s degree or equivalent practical experience.
- Eight years of experience in software development.
- Five years of experience testing and launching software products and three years of experience with software design and architecture.
- Five years of experience in speech/audio, reinforcement learning, ML infrastructure, or another ML specialization.
- Five years of experience with ML design and ML infrastructure, including model deployment, model evaluation, data processing, debugging, or fine-tuning.
- Experience integrating generative AI tools or LLM interfaces into workflows.
- Preferred qualifications include a PhD in machine learning, AI, computer science, statistics, applied mathematics, data science, or a related technical field.
- Preferred qualifications include AI research experience in a university or industry lab, deep knowledge of transformer internals and ML or distributed systems, compiler or performance engineering experience, high-performance computing, AI inference optimization, low-level compute frameworks, and a strong publication record in top AI venues.
Categories
AI ResearchML Engineering
About Google
Google builds consumer and enterprise software and services including Search, Android, YouTube, Chrome, Maps, Gmail, and Google Cloud. Its business model centers on digital advertising and paid cloud, software, and hardware offerings (e.g., Pixel and Nest) for consumers, developers, and organizations. Founded in 1998 and headquartered in Mountain View, California, Google operates globally as a subsidiary of Alphabet Inc.