16 hours ago
Base Salary
$174k - $252k/yr
Responsibilities
- Design, build, and maintain scalable performance simulation frameworks for next-generation TPU training and serving workloads.
- Model interactions between AI model architectures and hardware variables including SRAM, HBM, ICI topologies, and failover mechanisms.
- Develop AI-agentic platforms and toolchains for simulator sweep setup, parameter sensitivity analysis, data extraction, and bottleneck diagnosis.
- Build analytical and optimization engines using techniques such as Mixed-Integer Programming, simulated annealing, and roofline estimation.
- Produce performance projections and trade-off studies to inform TPU roadmaps and hardware contracts.
Requirements
- Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, a related technical field, or equivalent practical experience.
- At least 5 years of software engineering experience, including C++ and Python.
- Experience with computer architecture concepts such as memory hierarchies, roofline models, bandwidth versus compute bottlenecks, and network topologies.
- Experience designing software for simulation, performance modeling, or scientific computing.
- Preferred: Master’s degree or PhD in Computer Science or a related technical field.
- Preferred: experience with LLM-based agentic orchestration or applying AI to software engineering, hardware/compiler optimization, or simulation workflows.
- Preferred: experience with performance profiling tools, analytical roofline modeling, or architectural simulators.
- Preferred: knowledge of transformer architectures, distributed execution paradigms, and ML frameworks such as JAX, PyTorch/XLA, or Pallas.
- Preferred: ability to connect high-level model specifications with low-level hardware constraints such as interconnect latency, SRAM caching, and DMA scheduling.
Benefits
- US base salary of $174000-$252000, plus a 15% bonus target, equity, and benefits.
- Google benefits are provided; the posting refers applicants to Google’s benefits information.
Categories
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.