Agent System Backend Engineer Graduate (AML Ark) - 2027 Start

ByteDance; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

ByteDance is seeking engineers in Singapore to build Volcano Ark, an enterprise-grade Agent platform. You will design a scalable Agent runtime, implement platform capabilities, and integrate with OpenAPIs for external use.

You will help advance evaluation frameworks and performance under heavy workloads, while exploring new Agent paradigms and productionizing core capabilities. The role requires strong coding skills in Golang, Python, Rust, or Java, and familiarity with Linux, Docker, and

Qualifications

• Bachelor's or Master's degree in computing or a related discipline.
• Proficient in at least one of Golang, Python, Rust, or Java with hands-on AI-powered coding tools.
• Strong understanding of large language models and Agent architectures incl. tool calling and context management.
• Familiar with Linux, Docker, Kubernetes, and cloud-native infra; knowledge of distributed systems and observability.
• Experience with microservices, MySQL, Redis, and message queues; strong API design and data modeling.

Responsibilities

• Develop core Agent infrastructure for Volcano Ark platform, focusing on a reliable, scalable runtime and execution engine.
• Build platform capabilities: resource models, lifecycle/configuration management; integrate OpenAPIs with authentication, rate limiting, and metering.
• Design and develop an Agent evaluation framework with benchmarks and integration with leading harnesses; gather metrics and cost/latency analytics.
• Ensure high-concurrency performance and observability across the Agent platform.
• Stay at the frontier of Agent tech; drive productization and provide feedback-driven improvements.

Skills

Golang

Python

Rust

Java

Linux

Docker

Kubernetes

API design

Distributed systems

Observability

Education

Bachelor's/Master's degree in computing or related discipline

Tools

MySQL

Redis

Message queues

Job description

Responsibilities

Team Introduction Volcano Ark is Volcano Engine's one-stop foundation model and Agent platform for enterprises and developers. Our team is building the next-generation infrastructure for general-purpose Agents capable of handling complex tasks—from Agent runtimes and execution engines, to platform-level resource models, lifecycle management, and public APIs, as well as evaluation and observability systems. We are looking for talented individuals to join our team. As a graduate, you will get opportunities to pursue bold ideas, tackle complex challenges, and unlock limitless growth. Successful candidates must be able to commit to an onboarding date by the end of the year. Please state your availability and graduation date clearly in your resume. Candidates can apply to a maximum of two positions and will be considered for jobs in the order you apply. The application limit is applicable to our Company and its affiliates' jobs globally. Applications will be reviewed on a rolling basis - we encourage you to apply early.

• Develop the core Agent infrastructure for the Volcano Ark platform by designing and implementing a highly reliable, scalable Agent runtime and execution engine. Improve execution efficiency, security, and stability while building a general-purpose Agent infrastructure capable of supporting complex tasks.
• Build core platform capabilities, including resource model abstraction, lifecycle management, and configuration management. Integrate with the Volcano Engine Open Platform to deliver external-facing OpenAPIs, covering API registration, publishing, authentication, rate limiting, and metering & billing, ensuring reliability, compatibility, and operational stability.
• Design and develop the Agent evaluation framework by integrating industry-standard benchmarks. Enable compatibility with leading Agent harnesses including **Claude Code, Codex, and OpenCode**, while building a unified integration layer and execution protocol. Develop capabilities for metrics collection, trace replay, bad-case analysis, and cost/latency analytics to continuously improve the platform.
• Ensure the quality of online services under high-concurrency and large-scale workloads by building robust performance optimization, reliability, and observability capabilities across the Agent platform.
• Stay at the forefront of Agent technologies and AI-native applications by exploring next-generation Agent paradigms. Drive the productization of platform capabilities to improve developer productivity, while serving as a power user of the Agent platform to continuously refine and enhance its core capabilities through real-world feedback.

Qualifications

Minimum Qualifications:

• Individuals who are completing or have recently completed a Bachelor's/ Master's degree in computing or a related discipline.
• Solid coding skills and system design capabilities. Proficient in at least one of Golang, Python, Rust, or Java, with hands-on experience using AI-powered coding tools.
• Strong understanding of large language models and Agent architectures, including key concepts such as tool calling, context management, long-horizon execution, and self-invocation. Candidates with hands-on experience building production Agent systems or extensive experience using coding agents such as Claude Code, Codex, or Cursor are preferred.
• Familiar with Linux, container technologies (Docker, Kubernetes), and cloud-native infrastructure. Understanding of distributed systems, task scheduling, observability, resource isolation, and network access control. Experience with declarative APIs, the Kubernetes controller pattern, and Operator/CRD development is a plus.
• Backend & Distributed Services: Experienced in microservice architecture and common backend technologies such as MySQL, Redis, and message queues. Strong API design and data modeling skills. Experience designing and optimizing high-concurrency, low-latency online services is preferred.

Preferred Qualifications

• Familiar with container runtime, virtualization technologies (e.g., runC, gVisor, Kata Containers, Firecracker), serverless platforms, cloud provider PaaS, open platforms, multi-tenant systems, or large-scale data storage and retrieval systems.
• Passionate about AI-native applications and staying current with the latest advancements in Agent technologies. Able to demonstrate ability to rapidly reproduce research ideas and translate them into production-ready systems.

Job Information

About Us

Founded in 2012, ByteDance's mission is to inspire creativity and enrich life. With a suite of more than a dozen products, including TikTok, Lemon8, CapCut and Pico 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.

Why Join ByteDance

Inspiring creativity is at the core of ByteDance's mission. Our innovative products are built to help people authentically express themselves, discover and connect – and our global, diverse teams make that possible. Together, we create value for our communities, inspire creativity and enrich life - a mission we work towards every day. As ByteDancers, we strive to do great things with great people. We lead with curiosity, humility, and a desire to make impact in a rapidly growing tech company. By constantly iterating and fostering an "Always Day 1" mindset, we achieve meaningful breakthroughs for ourselves, our Company, and our users. When we create and grow together, the possibilities are limitless. Join us.

Diversity & Inclusion

ByteDance is committed to creating an inclusive space where employees are valued for their skills, experiences, and unique perspectives. Our platform connects people from across the globe and so does our workplace. At ByteDance, our mission is to inspire creativity and enrich life. To achieve that goal, we are committed to celebrating our diverse voices and to creating an environment that reflects the many communities we reach. We are passionate about this and hope you are too.