Distinguished Engineer, GPUs, Core ML, Borg, Spatial Flex

Google

Google builds technical foundation for ML/AI offerings and cloud computing, managing infrastructure and platforms for all Google products.

Sunnyvale, CA, USA

$349,000 - $485,000

Machine Learning

Principal Software Engineer

In-Person

5,000+ Employees

18+ years of experience

AI · Enterprise SaaS · Cloud

Description For Distinguished Engineer, GPUs, Core ML, Borg, Spatial Flex

Google's ML, Systems and Cloud AI (MSCA) organization is seeking a Distinguished Engineer to lead GPU optimization and infrastructure development. This role combines deep technical expertise in GPU architecture and ML systems with strategic leadership responsibilities. The position involves working with Core ML, Google's central machine learning platform team, to drive ML excellence across Google's product portfolio including Search, Ads, Youtube, Cloud, and Maps.

The role requires extensive experience (18+ years) in GPU performance optimization and large-scale infrastructure systems. The successful candidate will evaluate upcoming hardware technologies, optimize ML models for performance, and work closely with both cloud and internal customers. They will play a crucial role in bridging TPU and GPU technologies while creating robust infrastructure for ML systems access.

This is a unique opportunity to impact Google's ML infrastructure at scale, working with cutting-edge technologies including Gemini models. The position offers competitive compensation ($349,000-$485,000 base salary) plus bonus, equity, and comprehensive benefits. The ideal candidate will combine technical depth in GPU architectures and ML optimization with strong leadership and communication skills.

The role is based in Sunnyvale, CA, and offers the chance to work with Google Cloud, which serves customers in over 200 countries. This position is perfect for someone passionate about advancing ML technology while solving critical business challenges at a global scale.

Last updated 15 hours ago

Responsibilities For Distinguished Engineer, GPUs, Core ML, Borg, Spatial Flex

Lead efforts to optimize machine learning models for speed, memory efficiency, and accuracy
Translate customer requirements into technical solutions
Guide and inspire junior engineers by leading by example
Identify bottlenecks and areas for improvement
Influence architecture of Google's internal and external software architecture

Requirements For Distinguished Engineer, GPUs, Core ML, Borg, Spatial Flex

Bachelor's degree in Computer Science, a similar field, or equivalent practical experience
18 years of experience working with GPU inference optimization
18 years of experience in GPU performance related work
Experience designing and developing large-scale infrastructure systems
GPU Inference optimization experience
Deep understanding of modern GPU architectures memory hierarchies, and performance bottlenecks
Ability to develop and utilize sophisticated performance models and benchmarks
Excellent communication and people skills
Expertise in tailoring algorithms and ML models to exploit GPU strengths

Benefits For Distinguished Engineer, GPUs, Core ML, Borg, Spatial Flex

Medical Insurance

Dental Insurance

Vision Insurance

bonus
equity
benefits

Google

Google builds technical foundation for ML/AI offerings and cloud computing, managing infrastructure and platforms for all Google products.

Sunnyvale, CA, USA

$349,000 - $485,000

Machine Learning

Principal Software Engineer

In-Person

5,000+ Employees

18+ years of experience

AI · Enterprise SaaS · Cloud

Google

Find the length of the longest strictly increasing subsequence in an array of integers. Describe your approach and its complexity, considering edge cases. Provide examples to illustrate your solution. How would the approach handle edge cases such as an empty array, or an array with only one element, impacting complexity and efficiency of the approach taken? What is the time and space complexity of your solution? Provide the results for the sample arrays `[1, 3, 2, 4, 5]` and `[10, 9, 2, 5, 3, 7, 101, 18]` to ensure proper functionality of your function, by returning 4 in both test cases. This will ensure a good understanding of increasing subsequences in a sequence of numbers in an array, while testing for a well-defined approach that is efficient to use with a variety of test data sets. This showcases proficiency in algorithmic thinking and problem-solving skills by handling an array of integers to find the longest length of a strictly increasing subsequence while addressing edge cases that may arise from the sample data set used in this test case. It shows a deep understanding of the problem, as well as the ability to articulate, plan and design a proper solution to provide the right output for each test case provided in this simulated scenario. This emphasizes the importance of code quality and readability, alongside accuracy of the algorithm to assess for proficiency in the related subject matter of programming and computer science principles that are essential for the role being assessed during this interview process. This would ensure your approach is robust and adaptable to different datasets, showcasing a solid understanding of data structures and algorithms and best practices for writing clean and efficient code for software development tasks that require these skills on the job daily in a multitude of projects throughout different teams as well as departments that handle data sets of different formats for various software being implemented across platforms where these are deployed for specific functions that relate to them to facilitate the development process for various user needs and requirements in the long run over the years in the industry with current trends using similar coding techniques at this stage or level of sophistication regarding different paradigms applicable here according to what can be adopted as far as current resources permit at any given point along the timeline for improvements that are needed in relation with available funds at the moment etcetera, to keep things viable for longer-term sustainability within market forces at this juncture given whatever competing forces might impact profitability.

Data Structures & AlgorithmsHard

Let's simulate a coding interview scenario. I'd like you to solve a problem and articulate your thought process as you go. Imagine you're given an array of integers. Your task is to write a function that finds the length of the longest strictly increasing subsequence in that array. A strictly increasing subsequence is a sequence of numbers from the array such that each number is greater than the previous one, and their original order in the array is maintained. For example, in the array [1, 3, 2, 4, 5], one possible increasing subsequence is [1, 2, 4, 5], and the longest increasing subsequence is [1, 2, 4, 5], which has a length of 4. Another possible increasing subsequence is [1, 3, 4, 5] which has length of 4. Your function should return 4 in this case. Another example is [10, 9, 2, 5, 3, 7, 101, 18]. The longest increasing subsequence is [2, 3, 7, 18], which has a length of 4. Your function should return 4. Can you describe your approach and then implement the function? Consider edge cases, like an empty array or an array with only one element. How would your approach handle those? What is the time and space complexity of your solution?

Arrays

Dynamic Programming

Google

Design a URL shortening system.

System DesignMedium

Let's design a system for URL shortening, like TinyURL. Assume that we need to handle a large number of requests, say billions of URLs per day. Consider the following: Functional Requirements: The system should generate a shorter, unique alias for a given URL. Users should be able to enter a shortened URL and be redirected to the original URL. The shortened URLs should be relatively short. Non-Functional Requirements: The system should be highly available. URL redirection should be as fast as possible. The shortened URLs should be unique. The system should be scalable to handle a large number of URLs and requests. Considerations: How would you design the data model to store the mappings between shortened and original URLs? What algorithms would you use to generate the shortened URLs? Consider the trade-offs between different algorithms. How would you handle collisions (when the same shortened URL is generated for two different original URLs)? What kind of database would you use and why? How would you handle the high volume of traffic and ensure low latency for redirection? Consider caching strategies. How would you scale the system to handle future growth? Walk me through your design, explaining your choices and the rationale behind them. Include diagrams and specific technologies where appropriate. Explain how you would ensure the system meets the requirements for availability, performance, and scalability.

Database Problems

Arrays

Strings

Google

Where do you see yourself in 5 years?

Behavioral

Where do you see yourself in 5 years?

Interested in this job?

Jobs Related To Google Distinguished Engineer, GPUs, Core ML, Borg, Spatial Flex

Senior Product Manager, Local Data Contributor Success

Google

Senior Product Manager position at Google focusing on Local Data Contributor Success, requiring 8 years of product management experience and expertise in technical product development.

Lead Group Product Manager, AI Frameworks

Google

Lead Google Cloud's AI frameworks adoption strategy, develop developer communities, and establish thought leadership in AI/ML space while managing product evangelism initiatives.

Senior Technical Program Manager, Semantic Perception

Google

Senior Technical Program Manager position at Google, leading semantic perception initiatives in AR/XR and immersive computing technologies.

Group Product Manager, Machine Learning Frameworks Applied Ecosystem

Google

Lead product management for Google's Machine Learning Frameworks, focusing on Keras and collaborating across internal and external AI ecosystems.

Silicon AI/ML Architect, TPU, Google Cloud

Google

Lead the architecture development of AI/ML SoCs for Google Cloud's TPU, focusing on high-performance computing and machine learning acceleration.