Staff Software Engineer, Inference Performance Optimization, GenAI, DeepMind
Summary
Staff engineer at Google DeepMind optimizing AI model inference performance by designing inference optimization techniques, building investigative tools and metrics, modeling latency-to-cost tradeoffs, and resolving performance bottlenecks in GenAI workloads.
- Analyze and optimize AI inference workloads
- Design and implement inference optimization techniques
- Develop investigative tools and metrics
- Investigate and resolve model inference performance bottlenecks
- Model latency to cost impacts