Software Engineer, AI Infrastructure

undefined ago • All levels • Devops

Job Summary

Job Description

Our team builds a highly available and scalable general-purpose Serverless platform (FaaS) at ByteDance, handling over 100M+ QPS. We enable one-click function creation and deployment, abstracting infrastructure complexities to reduce developer burden. The platform dynamically scales functions for optimized resource utilization and costs, leveraging lightweight execution and rapid startup. We are seeking innovative engineers to develop AI Agent Ecosystems, design secure sandbox infrastructure for large model inference, enhance the FaaS platform's usability and scalability, architect global high-availability with NoOps capabilities, and optimize cold start performance for demanding serverless functions.
Must have:
  • Develop AI Agent Ecosystems: Contribute to designing and building AI agent frameworks, tool integration systems, and multi-agent collaboration platforms.
  • Design Secure Sandbox Infrastructure: Lead the development of sandbox technologies to support secure and efficient large model inference and training workloads.
  • Enhance Serverless Platform: Drive the design and evolution of our FaaS platform, focusing on usability, scalability, and cost optimization for enterprise users.
  • Build Global High-Availability Architecture: Architect automated disaster recovery and fault tolerance mechanisms across multi-cluster and multi-region environments to achieve NoOps capabilities.
  • Optimize Cold Start Performance: Innovate solutions for large-scale cold start scenarios, delivering multi-layered optimization to meet the demanding requirements of serverless functions.
Good to have:
  • containerization
  • networking
  • distributed tracing
Perks:
  • Inspiring creativity
  • global, diverse teams
  • create value for our communities
  • enrich life
  • inclusive space
  • valued for their skills, experiences, and unique perspectives

Job Details

Team IntroductionOur team is dedicated to building a highly available and scalable general-purpose Serverless platform that embodies the philosophy of Function-as-a-Service (FaaS). By enabling one-click function creation and deployment while abstracting infrastructure and operational complexities, we significantly reduce developers' burdens in both development and maintenance. Leveraging lightweight function execution and rapid startup capabilities, our platform dynamically scales functions to optimize resource utilization and costs. Currently handling 100M+ QPS, our architecture and product scale are industry-leading. We seek innovative, passionate engineers with experience in high-availability systems to join us in pioneering the future of serverless computing.

Responsibilities

  • Develop AI Agent Ecosystems: Contribute to designing and building AI agent frameworks, tool integration systems, and multi-agent collaboration platforms.
  • Design Secure Sandbox Infrastructure: Lead the development of sandbox technologies to support secure and efficient large model inference and training workloads.
  • Enhance Serverless Platform: Drive the design and evolution of our FaaS platform, focusing on usability, scalability, and cost optimization for enterprise users.
  • Build Global High-Availability Architecture: Architect automated disaster recovery and fault tolerance mechanisms across multi-cluster and multi-region environments to achieve NoOps capabilities.
  • Optimize Cold Start Performance: Innovate solutions for large-scale cold start scenarios, delivering multi-layered optimization to meet the demanding requirements of serverless functions.

Qualifications

Minimum Qualifications:

  • Strong Programming Fundamentals: Proficiency in algorithms, data structures, and at least one programming language (Go, Python, Java, Node.js, Rust, C).
  • Distributed Systems Expertise: Hands-on experience with large-scale distributed systems, including system modeling and problem-solving in production environments.
  • Cloud Native Experience: Familiarity with Kubernetes, Knative, Firecracker, or similar open-source projects.
  • Serverless Product Knowledge: Experience with AWS Lambda, Google Cloud Functions, or equivalent platforms.

Preferred Qualifications:

  • Familiarity with containerization, networking, and distributed tracing. If you're passionate about pushing the boundaries of serverless computing and thrive in fast-paced, innovative environments, we want to hear from you!

Similar Jobs

Looks like we're out of matches

Set up an alert and we'll send you similar jobs the moment they appear!

Similar Skill Jobs

Looks like we're out of matches

Set up an alert and we'll send you similar jobs the moment they appear!

Jobs in Singapore

Looks like we're out of matches

Set up an alert and we'll send you similar jobs the moment they appear!

Devops Jobs

Looks like we're out of matches

Set up an alert and we'll send you similar jobs the moment they appear!

About The Company

Founded in 2012, ByteDance's mission is to inspire creativity and enrich life. With a suite of more than a dozen products, including TikTok as well as platforms specific to the China market, including Toutiao, Douyin, and Xigua, ByteDance has made it easier and more fun for people to connect with, consume, and create content.
View All Jobs

Get notified when new jobs are added by bytedance

Level Up Your Career in Game Development!

Transform Your Passion into Profession with Our Comprehensive Courses for Aspiring Game Developers.

Job Common Plug