Backend Engineer, ARK Large Model Platform (Singapore)

ByteDance
Singapore
Workplace: OnsiteFull timeFunction: Software EngineeringExperience: 3+ yearsEducation: bachelorsSkills: ["Technical design","Coding skills","System stability focus","Team cooperation","Balancing technical perspectives with product sense"]

Build and evolve core backend pipeline components for the Ark MaaS (Model as a Service) platform, enabling API-driven text conversations and multimodal understanding/generation. Drive cloud-native architecture improvements including service mesh, load balancing, and intelligent routing, while implementing high-availability controls like canary releases, circuit breaking, and rate limiting. Optimize low-latency, high-throughput large-model multimodal inference and ensure stability during traffic surges.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
ByteDance
ByteDance
1 month ago

Backend Engineer, ARK Large Model Platform (Singapore)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 30 days agoStatus: Live
Reposted: similar role first listed 1 month ago

Job Summary

Build and evolve core backend pipeline components for the Ark MaaS (Model as a Service) platform, enabling API-driven text conversations and multimodal understanding/generation. Drive cloud-native architecture improvements including service mesh, load balancing, and intelligent routing, while implementing high-availability controls like canary releases, circuit breaking, and rate limiting. Optimize low-latency, high-throughput large-model multimodal inference and ensure stability during traffic surges.
Location: Singapore
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering
Seniority: Mid level

Key Responsibilities

  • •Design and develop core pipeline components for the Ark MaaS (Model as a Service) platform, supporting API capabilities for text conversations and multimodal understanding/generation.
  • •Evolve cloud-native architectures using service mesh, load balancing, and intelligent routing; implement high-availability patterns such as full-link canary releases, circuit breaking, and rate limiting.
  • •Optimize system performance for large-model multimodal inference, addressing long connections, high throughput, streaming output, and low-latency requirements.
  • •Ensure stability under large-scale model invocation and resolve architectural bottlenecks from sudden traffic surges.

Key Requirements

  • •B. Sc (or higher) in Computer Science or a related field with at least 3 years of relevant experience.
  • •Familiarity with development and operations of distributed systems on Linux.
  • •Proficiency in at least two programming languages such as Golang, Python, C/C++, Java, Scala, or JavaScript.
  • •Strong technical design and coding skills, with the ability to balance technical tradeoffs with product sense and stability.
  • •Preferred: hands-on experience building agents, including Function Calling and MCP.
Experience:3+ years
Education:Bachelor's in Computer Science
Skills:Technical designCoding skillsSystem stability focusTeam cooperationBalancing technical perspectives with product sense
Tech Stack:LinuxGolangPythonCC++JavaScalaJavascriptService MeshLoad balancingKubernetesDockerIstioEnvoyMCPFunction CallingLLM inference pipelinesMultimodal data processing

Company Brief

ByteDance
Develops consumer internet and content platforms, including TikTok and other apps for short-form video, news, and entertainment. It also builds advertising, commerce, and creator tools that connect audiences, brands, and publishers across global markets.
Industry: Digital Media
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Established Company
Headquarters: Beijing, China
Founded: 2012
WebsiteLinkedIn