Responsibilities
- Optimize distributed scheduling and orchestration strategies to improve cluster utilization and resource efficiency.
- Develop and integrate autoscaling, automatic parallelization, resource preemption and eviction, mixed-resource deployment, and scheduling across data centers, regions, and clouds.
- Build distributed training runtimes for ultra-large-scale embeddings and GPU synchronization.
- Design distributed computing APIs and runtime systems for recommendation and advertising model workflows including reinforcement learning, fine-tuning, and distillation.
- Improve the diagnosability and usability of distributed training platforms.
- Build distributed online model inference architecture for large-scale embedding and recommendation workloads.
- Improve recommender-system online architecture and ML operations processes by integrating business research and experimentation models.
Requirements
- Bachelor's degree or above in Computer Science or a related field.
- At least 5 years of experience and strong hands-on proficiency in Go or Python in a Linux environment.
- Experience with distributed scheduling frameworks such as Kubernetes, Godel, YARN, Mesos, or Celery, and with machine learning systems.
- Experience designing, developing, and maintaining large-scale distributed systems, with a strong understanding of distributed-systems principles.
- Strong logical analysis, business abstraction, communication, learning, documentation, and execution skills.
- Preferred experience with PyTorch or TensorFlow.
- Preferred experience in AI infrastructure, hardware/software co-design, high-performance computing, or ML hardware architecture involving GPUs, accelerators, or networking.
- Preferred experience designing or using training orchestration systems such as veRL, vLLM, Ray, or TFX.
Tech Stack
Categories
About ByteDance
ByteDance is a global incubator of platforms at the cutting edge of commerce, content, entertainment and enterprise services - over 2.5bn people interact with ByteDance products including TikTok. Creation is the core of ByteDance's purpose. Our products are built to help imaginations thrive. This is doubly true of the teams that make our innovations possible. Together, we inspire creativity and enrich life - a mission we aim towards achieving every day. At ByteDance, we create together and grow together. That's how we drive impact - for ourselves, our company, and the users we serve. We are committed to building a safe, healthy and positive online environment for all our users. We have over 110,000 employees based in more than 30 countries globally. Join us.