ByteDance
Machine Learning Engineer - Inference
San Jose, California · Full-time · Posted Oct 28, 2026
- Experience
- At least 3 years of experience developing and deploying large-scale systems.
About the job
Designs and improves distributed inference infrastructure and tools for feeds, ads, and search ranking models.
What you'll do
- Design and implement distributed inference infrastructure for ranking models.
- Build tools to monitor and manage the reliability and scalability of online inference servers.
- Analyze system bottlenecks and instability, improve performance, and collaborate with product teams on solutions.
What they ask for
- At least 3 years of experience developing and deploying large-scale systems.
- Experience contributing to an open-sourced machine learning framework.
- Strong background in Hardware-Software Co-Design, High Performance Computing, ML Hardware Acceleration, or ML for Systems.
Tools
tensorflow, jax, pytorch, torchscript, mxnet, tensorrt, GPU, RDMA
AI focus
Advances machine-learning inference infrastructure for ads, search, feeds, live, and e-commerce ranking.
Model-written summary · the original posting is authoritative