Software Engineer, Voxel, JIT and Hardware Accelerated GoogleSQL

Google•San Jose, CA

3h•$147,000 - $211,000

About The Position

Google's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information and one another. Our products need to handle information at massive scale, and extend well beyond web search. We're looking for engineers who bring fresh ideas from all areas, including information retrieval, distributed computing, large-scale system design, networking and data storage, security, artificial intelligence, natural language processing, UI design and mobile; the list goes on and is growing every day. As a software engineer, you will work on a specific project critical to Google’s needs with opportunities to switch teams and projects as you and our fast-paced business grow and evolve. We need our engineers to be versatile, display leadership qualities and be enthusiastic to take on new problems across the full-stack as we continue to push technology forward. In this role on the Voxel team, you will be at the forefront of optimizing GoogleSQL query execution through compiler technologies. You will be a key contributor to a Core Innovation Fund project focused on bringing Just-in-Time (JIT) compilation and hardware acceleration to GoogleSQL. You will help design, develop, and implement a unified, hardware-agnostic compilation framework leveraging Multi-Level Intermediate Representation (MLIR). You will enable GoogleSQL queries to be efficiently compiled and executed across Google's various hardware fleet, including CPUs, GPUs, and TPUs, unlocking significant performance and resource efficiency. In this role, you will have an an opportunity to gain valuable expertise in a high-impact area, driving innovation in query execution to support Google's growing AI/ML infrastructure needs and contributing to strategic AI initiatives such as vector search and efficient data preparation.

Requirements

Bachelor's degree or equivalent practical experience.
2 years of experience coding in C++.
2 years of experience with code optimization.
2 years of experience with data structures.

Nice To Haves

Master's degree or PhD in Computer Science or a related technical field.
2 years of experience with compliers.
2 years of experience with JIT Compiler.
2 years of experience with JIT Compiler.
2 years of experience with SQL and GoogleSQL.
2 years of experience with open source technologies.

Responsibilities

Build a unified, hardware-agnostic compilation framework for GoogleSQL execution, in support of the Core Innovation Fund project "JIT-Compiled and Hardware Accelerated GoogleSQL Execution".
Design and implement efficient kernels for SQL operations across CPUs, GPUs, and TPUs.
Leverage MLIR to translate GoogleSQL into highly optimized code for heterogenous hardware.
Drive query execution optimization on GPU/TPU through a hybrid approach that combines JIT compilation, vectorized execution, and accelerator offloading.
Conduct rigorous performance analysis and tuning of the JIT-compiled code on different hardware platforms, and optimize the implementations to address bottlenecks.