Community

Home >

Jobs >

Software Engineer, Edge TPU Developer Tools

Software Engineer, Edge TPU Developer Tools

1 Month ago • 5-8 Years • Research & Development

About the job

4 skills required for this role

Add these skills to join the top 1% applicants for this job

cpp

algorithms

data-structures

networking

Job Description

As a Software Engineer, you'll develop tooling for the Tensor TPU SoC SDK to accelerate complex machine learning models on custom hardware accelerators. You'll build tools complementing the compiler to efficiently map ML models to the hardware ISA, focusing on always-on computing. Responsibilities include designing and implementing methods to gather performance metrics, correlating performance data at the ML graph or hardware level, building performance analysis tools for simulators or new hardware, and creating user-facing materials (codelabs, documentation, tutorials) to guide users in analyzing and improving latency, accuracy, and power. This role sits at the intersection of ML accelerators, optimization, embedded systems, and is critical for customers deploying models on consumer hardware.

Must have:

5+ years software development experience
3+ years building developer tools
3+ years software product development
Experience with data structures/algorithms
Build tools for efficient ML model mapping
Design & implement performance metric gathering

Good to have:

Master's/PhD in CS (compiler/ML focus)
Experience with domain-specific ML compilers
C++ programming experience
Developer tools for APU, NPU, GPU, DSP
Power/performance optimization experience
Low-level tooling (profiling, tracing)

Minimum qualifications:

Bachelor’s degree or equivalent practical experience.
5 years of experience with software development in one or more programming languages, and with data structures/algorithms.
3 years of experience building developer tools (e.g., compilers, automated releases, code design and testing, test automation frameworks).
3 years of experience in developing software products, and 1 year of experience with software design and architecture.

Preferred qualifications:

Master's degree or PhD in Computer Science or related technical field with an emphasis on compiler or ML performance.
Experience with domain-specific compilers for machine learning and experience with using C++ as programming language.
Experience in building developer tools for computing accelerators such as APU, NPU, GPU and DSP.
Experience in power and performance optimizations.
Experience with low-level and low intrusiveness developer tooling concepts such as profiling, instrumentation, API tracing, hardware tracing.
Understanding of hardware, especially hardware that provides a degree of parallelism.

About the job

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.

As a Software Engineer you will work on developing toolings as part of SoC Software Development Kit (SDK) for the Tensor TPU to accelerate complex machine learning models running on custom hardware accelerators. Along with your technical expertise, you will manage project priorities, deadlines and deliverables.

This opportunity sits at the intersection of Machine Learning (ML) accelerators, optimization and deployment of ML models, embedded systems, and will be on the critical path of customers looking to productionize their models on consumer hardware.

Google's mission is to organize the world's information and make it universally accessible and useful. Our team combines the best of Google AI, Software, and Hardware to create radically helpful experiences. We research, design, and develop new technologies and hardware to make computing faster, seamless, and more powerful. We aim to make people's lives better through technology.

Responsibilities

Build tools that compliments compiler to efficiently map ML models (with a particular focus on always-on computing use cases) to the hardware ISA.
Design and implement new ways to gather useful performance metrics from hardware or software stack.
Design and implement tools that can correlate performance data at a ML graph level or logical hardware level.
Build performance analysis tools for simulators or new hardware.
Show users how to use our tools to analyze, debug and improve latency, accuracy, and power through codelabs, documentation, and tutorials.

View Full Job Description

Upload your resume, increase your shortlisting chances by 80%

About The Company

Google

3049 Active Jobs

A problem isn't truly solved until it's solved for all. Googlers build products that help create opportunities for everyone, whether down the street or across the globe. Bring your insight, imagination and a healthy disregard for the impossible. Bring everything that makes you unique. Together, we can build for everyone.