Backend Engineer, ARK Large Model Platform (Singapore)

United States Digital Space LLC; Singapore; On-site; SGD 90,000 - 120,000; Full time

Job summary

VolcanoEngine's AML - Ark team is seeking engineers to design and develop core pipeline components for the Ark MaaS platform, enabling API capabilities for text conversations, multimodal understanding, and generation.

You will participate in evolving cloud-native architectures and implement highly available solutions, focusing on low latency and high throughput for large-model multimodal tasks.

Qualifications

• B. Sc or higher in Computer Science or related fields with 3+ years of experience.
• Distributed systems know-how on Linux.
• Proficient in multiple programming languages listed above.
• Strong technical design and coding skills; balance tech and product needs.

Responsibilities

• Design and develop core pipeline components for Ark MaaS platform (Model as a Service).
• Contribute to cloud-native architectures including Service Mesh, LB, and intelligent routing.
• Optimize large-model multimodal inference with high throughput and low latency.
• Ensure stability under high traffic and resolve bottlenecks.

Skills

Golang

Python

C

C++

Java

Scala

JavaScript

Competitive programming

Linux

System design

Multimodal data

LLM inference

Education

Bachelor's degree in CS or related field

Tools

Kubernetes

Docker

Istio

Envoy

Job description

About the Team

The Applied Machine Learning (AML) - Ark team provides machine learning platform products on VolcanoEngine with cloud native resource scheduling system which intelligently orchestrates different tasks and jobs with minimised costs of every experiment and maximised resource utilisation, rich modelling tools including customised machine learning tasks and web IDE, and multi-framework high performance model inference services.

In 2021, through VolcanoEngine, we released this machine learning infrastructure to the public, to provide more enterprises with reduced costs of computation power, lower barriers to machine learning engineering and deeper developments in AI capabilities.

Responsibilities

• Design and develop core pipeline components for the Ark MaaS platform (Model as a Service), supporting API capabilities such as text conversations, multimodal understanding, and multimodal generation.
• Participate deeply in the evolution of cloud-native architectures, including Service Mesh, load balancing (LB), and intelligent routing. Design and implement highly available solutions such as full-link canary releases, traffic degradation, circuit breaking, and rate limiting.
• Optimize system performance for large-model multimodal inference scenarios involving long connections, high throughput, streaming output, and low-latency requirements.
• Ensure system stability under large-scale model invocation scenarios and resolve architectural bottlenecks caused by sudden traffic surges.

Qualifications

Minimum Qualifications

• B. Sc or higher degree in Computer Science or related fields from accredited and reputable institutions with at least 3 years of relevant experience.
• Familiar with developments and operations of distributed systems under Linux platform.
• Proficient with at least 2 or more programming languages such as Golang / Python / C / C++ / Java / Scala / Javascript. ACM ICPC / Codeforces winners are preferred.
• Excellent in technical design and coding skills. Able to balance technical perspectives with product sense, hardware performance & stability and team cooperation.

Preferred Qualifications

• Understanding of Agent-related concepts and technologies such as Function Calling and MCP; hands-on experience building Agents is a plus.
• Familiarity with cloud-native and Service Mesh technologies such as Kubernetes, Docker, Istio, and Envoy.
• Strong understanding of multimodal data processing and storage, including image and video/audio data.
• Interest in or practical experience with LLM inference pipelines and large-model engineering systems.