Silicon AI/ML Lead Architect

Google

Google is a global technology company that develops innovative products and services used by millions worldwide.

Bengaluru, Karnataka, India

Machine Learning

Principal Software Engineer

In-Person

10+ years of experience

Description For Silicon AI/ML Lead Architect

Google is seeking a Silicon AI/ML Lead Architect to join their Technical Infrastructure team, focusing on developing custom silicon solutions for AI accelerators in data centers. This role combines hardware architecture expertise with AI/ML technology, working on next-generation data center accelerators.

The position offers a unique opportunity to shape the future of Google's AI infrastructure, working with cutting-edge technology in custom silicon development. You'll be responsible for evaluating and implementing various silicon solutions, from off-the-shelf components to custom designs and chiplets, while collaborating with cross-functional teams to ensure optimal performance and efficiency.

As a Lead Architect, you'll play a crucial role in developing the hardware that powers Google's AI initiatives, requiring deep expertise in micro-architecture, ASIC design, and modern AI/ML systems. The role demands both technical leadership and collaborative skills, working with software teams to optimize hardware/software interfaces and ensure seamless integration.

This position is perfect for someone who combines deep technical knowledge in silicon design with a passion for AI/ML technologies. You'll be working with a diverse team that pushes boundaries and develops solutions that directly impact Google's products used by millions worldwide. The role offers the opportunity to work on challenging problems at the intersection of hardware architecture and artificial intelligence, making a significant impact on the future of Google's AI infrastructure.

Last updated 3 months ago

Responsibilities For Silicon AI/ML Lead Architect

Evaluate different silicon solutions for executing Google's data center AI accelerator roadmap
Create high performance hardware/software interfaces
Collaborate with software, verification, emulation, physical design, packaging, and silicon validation stakeholders
Own microarchitecture of compute intensive Internet Protocols (IP) and subsystems
Identify and drive power, performance, and area improvements for the modules owned

Requirements For Silicon AI/ML Lead Architect

Python

Bachelor's degree in Electrical Engineering or equivalent practical experience
10 years of experience in micro-architecture and design of graphics or Machine Learning (ML) Internet Protocols (IP)
5 years of experience architecting networking ASICs from specification to production
Experience developing RTL for ASIC subsystems using SystemVerilog
Experience in micro-architecture, design, verification, logic synthesis, and timing closure
Knowledge of arithmetic units, bus architectures, accelerators, or memory hierarchies
Knowledge of high performance and low power design techniques
Proficiency in a procedural programming language (C++, Python, Go)

Google

Google is a global technology company that develops innovative products and services used by millions worldwide.

Bengaluru, Karnataka, India

Machine Learning

Principal Software Engineer

In-Person

10+ years of experience

Google

How would you sort an unsorted array of integers in ascending order using the merge sort algorithm, without using built-in sorting functions? Explain merge sort, its implementation, efficiency and how it can be modified for descending order or implemented iteratively.

Data Structures & AlgorithmsHard

Given an unsorted array of integers, write a function to sort the array in ascending order using the merge sort algorithm. Explanation of Merge Sort:** Briefly explain the merge sort algorithm, highlighting its divide-and-conquer approach. Implementation:** Provide a step-by-step implementation of the merge sort algorithm. This includes: A mergeSort function that recursively divides the array into smaller subarrays. A merge function that merges two sorted subarrays into a single sorted array. Example:** Input array: [38, 27, 43, 3, 9, 82, 10] Expected output: [3, 9, 10, 27, 38, 43, 82] Efficiency:** Discuss the time and space complexity of merge sort. Why is merge sort considered an efficient sorting algorithm? How does it compare to other sorting algorithms like bubble sort or quicksort in terms of performance (best, average, and worst-case scenarios)? Constraints:** You are not allowed to use built-in sorting functions. The array can contain positive and negative integers. The solution must be implemented in a language of your choice (e.g., Python, Java, C++). Follow-up:** How would you modify the merge sort algorithm to sort the array in descending order? Could you implement an iterative version of merge sort instead of the recursive one? What are the trade-offs?

Arrays

Recursion

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 Silicon AI/ML Lead Architect

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.