Software Engineer Graduate (AML-Engine-Orchestration) - 2027 Start (PhD)

ByteDance
Seattle
Workplace: OnsiteFull timeFunction: Software EngineeringEducation: phdSkills: ["Ownership","Collaboration","Problem-solving","Quantitative thinking","Exploratory investigation"]

Build ML infrastructure that powers online model serving across ByteDance products, including TikTok. You’ll design and implement orchestration and scheduling systems—covering Kubernetes Operators, container lifecycle management, multi-tenant quota and preemption, and multi-cluster resource orchestration. Work on serving orchestration such as model/image distribution, deployment upgrades/rollback, autoscaling, disaster recovery, and traffic management for low-latency, reliable inference.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
ByteDance
ByteDance
2 days ago

Software Engineer Graduate (AML-Engine-Orchestration) - 2027 Start (PhD)

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 14 hours agoStatus: Live

Job Summary

Build ML infrastructure that powers online model serving across ByteDance products, including TikTok. You’ll design and implement orchestration and scheduling systems—covering Kubernetes Operators, container lifecycle management, multi-tenant quota and preemption, and multi-cluster resource orchestration. Work on serving orchestration such as model/image distribution, deployment upgrades/rollback, autoscaling, disaster recovery, and traffic management for low-latency, reliable inference.
Location: Seattle
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering
Seniority: Graduate level

Key Responsibilities

  • •Design and build foundational orchestration capabilities for ML platforms, including Kubernetes Operators, container runtimes, and lifecycle management for jobs, services, and stateful workloads.
  • •Build multi-tenant resource and quota systems supporting priorities, preemption, fair sharing, elasticity, and cross-cluster scheduling to improve GPU utilization and cost efficiency.
  • •Implement lifecycle orchestration for online model serving, including model/image distribution, deployment, upgrades, rollback, autoscaling, multi-cluster operation, and disaster recovery.
  • •Develop serving orchestration and traffic management for disaggregated serving clusters, including topology-aware scheduling, KV cache affinity, intelligent request routing, and QoS/SLA management.

Key Requirements

  • •Completing or recently completed a PhD in Computer Science, Software Engineering, Artificial Intelligence, or a related technical field.
  • •Proficiency in at least one of Go, C++, or Python, with strong data structures and algorithms and software engineering fundamentals.
  • •Familiarity with Linux plus foundational understanding of operating systems, computer networks, concurrent programming, and distributed systems.
  • •Strong hands-on exploratory skills using source code, metrics, logs, profiling, and experiments to investigate systems.
  • •A systematic, quantitative approach to problem solving, including defining measurements, testing hypotheses, and validating improvements.
Experience:Machine learningModel servingDistributed systemsOpen sourceCloud infrastructure
Education:PhD / Doctorate
Skills:OwnershipCollaborationProblem-solvingQuantitative thinkingExploratory investigation
Tech Stack:GoC++PythonLinuxKubernetesKubernetes OperatorsContainer runtimesFinOpsVolcanoKoordinatorOpenKruiseVLLMSGLangTritonKServeRay ServeKV CacheContinuous BatchingPrefill/DecodeModel parallelism

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