Staff GenAI Inference Performance Engineer

Google; Mountain View (CA); On-site; USD 207,000 - 300,000; Full time

Benefits offered by this job

Equity

Bonus target

Benefits

Job summary

Google DeepMind is seeking a Staff Software Engineer focused on Inference Performance Optimization for GenAI. Based in Mountain View, you will drive optimization of AI inference workloads, design fast serving techniques, and analyze bottlenecks to maximize throughput and minimize latency across distributed systems.

You will work with a mission-driven team advancing AI agents, with emphasis on scalable inference, profiling, and performance engineering.

Qualifications

• Bachelor's degree or equivalent practical experience in CS/CE/Applied Math or related field.
• 8 years of software development experience.
• Experience in Python and C++, including navigating, debugging, and modifying serving codebases.
• Experience with AI model execution constraints and modern serving architectures.

Responsibilities

• Analyze and optimize AI inference workloads to 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 latency-to-cost impacts and translate insights into actionable production signals.
• Develop investigative tools and metrics to track compute usage across the fleet.

Skills

Python

C++

Debugging

Serving architectures

Education

Bachelor's degree or equivalent experience

Job description

Google DeepMind is seeking a Staff Software Engineer focused on Inference Performance Optimization for GenAI. Based in Mountain View, you will drive optimization of AI inference workloads, design fast serving techniques, and analyze bottlenecks to maximize throughput and minimize latency across distributed systems.

You will work with a mission-driven team advancing AI agents, with emphasis on scalable inference, profiling, and performance engineering.