ByteDance
Senior Software Engineer - AI Compute Infrastructure
Seattle, Washington · Senior · Full-time · Posted Oct 28, 2026
- Experience
- 3+ years of relevant experience; Ph.D. with strong systems/ML publications also considered.
- Education
- B.S./M.S. in Computer Science, Computer Engineering, or related fields; Ph.D. with strong systems/ML publications also considered.
About the job
Build and operate scalable, cloud-native cluster orchestration and GPU infrastructure for large-scale AI and LLM inference workloads.
What you'll do
- Design and build high-performance, resilient container-based cluster management and orchestration systems.
- Architect cost-efficient, secure GPU and AI accelerator infrastructure.
- Collaborate on inference solutions using LLM engines and deliver maintainable, production-ready code.
What they ask for
- Strong understanding of large model inference, distributed and parallel systems, and/or high-performance networking.
- Hands-on experience building cloud or ML infrastructure, such as resource management, scheduling, routing, monitoring, or orchestration.
- Knowledge of Docker and Kubernetes.
- Proficiency in at least one of Go, Rust, Python, or C++.
Nice to have
- Experience with large-scale cluster systems, production GPU orchestration or scheduling, GPU programming, or inference engines.
- Familiarity with public cloud and ML platforms, ML systems, or distributed training and inference platforms.
Tools
AIBrix, Kubernetes, Docker, Go, Rust, Python, C++, vLLM
AI focus
Develop GPU-optimized infrastructure and platforms for large-scale LLM inference, integrating inference engines such as vLLM, SGLang, and TensorRT-LLM.
Model-written summary · the original posting is authoritative