The Staff Software Engineer role at DeepMind focuses on inference performance optimization for AI models. The position involves working with advanced AI agents and requires a strong foundation in software engineering. The team aims to enhance the efficiency of large-scale AI inference, addressing complex performance bottlenecks. This role combines deep systems profiling and benchmarking to maximize hardware throughput and reduce costs.

• Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics, or a related technical field, or equivalent practical experience.
• 8 years of experience in software development.
• Experience in Python and C++, including navigating, debugging, and modifying serving codebases.
• Experience with AI model execution constraints, throughput-latency tradeoffs, memory bandwidth limitations, and modern serving architectures.

• Analyze and optimize AI inference workloads across the application, model, and distributed fleet infrastructure layers to methodically increase throughput-per-GPU and reduce latency.
• Design and implement inference optimization techniques.
• Investigate and resolve complex model inference performance bottlenecks across the stack.
• Model the latency-to-cost impacts of system variables and translate these insights into actionable signals that drive production systems.
• Develop investigative tools and metrics that track where compute is spent across the fleet.

• Employees at Google are often offered benefits like comprehensive health insurance, 401(k) matching, and flexible work arrangements, among other benefits.