About the role#
The Data-AML-Engine Orchestration team builds large-scale machine learning infrastructure for products like TikTok. We develop the orchestration, scheduling, and resource management systems that connect compute infrastructure with production machine learning workloads. You will work on systems that impact GPU utilization, serving latency, infrastructure reliability, and developer productivity.
What you'll need#
- Currently pursuing a Bachelor's or Master's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field.
- Proficiency in Go, C++, or Python.
- Solid foundation in data structures, algorithms, and software engineering.
- Familiarity with Linux and a foundational understanding of operating systems, computer networks, concurrent programming, and distributed systems.
- A systematic approach to problem solving, including the ability to define measurements, test hypotheses, and validate system improvements.
- Demonstrated ownership through coursework, research, internships, or open-source projects.
- Experience with Kubernetes, container runtimes, resource scheduling, or multi-tenant systems is preferred.
- Experience with model serving systems like vLLM, SGLang, Triton, KServe, or Ray Serve is a plus.
- Familiarity with GPU/NPU programming or inference performance analysis is helpful.
What you'll do#
- Design and build foundational machine learning platform orchestration, including Kubernetes Operators, container runtimes, and lifecycle management for jobs and services.
- Build multi-tenant resource and quota systems that support priorities, preemption, fair sharing, elasticity, and cross-cluster scheduling.
- Improve GPU utilization and cost efficiency through resource pooling and FinOps.
- Develop lifecycle orchestration for online model serving, such as model distribution, deployment, upgrades, rollbacks, autoscaling, and disaster recovery.
- Build serving orchestration and traffic management for disaggregated serving clusters, including topology-aware scheduling, KV Cache affinity, request routing, and QoS management.
Location & details#
- Location: Seattle, Washington.
- Role type: Full-time intern.
- Modality: On-site.
- Term: Rolling basis.


