AI Infrastructure Engineer (LLM Training & Inference)

ByteDance; San Jose (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical Insurance

Dental Insurance

Vision Insurance

401(k) Savings Plan With Company Match

Paid Parental Leave

Short-term Disability Coverage

Long-term Disability Coverage

Life Insurance

Wellbeing Benefits

Paid Holidays

Paid Sick Days

Paid Personal Time

Job summary

ByteDance is seeking to develop and optimize core AI infrastructure technologies, covering training, inference, and AI agents. The role involves cutting-edge research collaboration with academia and open-source communities to advance the state of the art.

The position expects a strong foundation in computer science and hands-on experience with LLM tooling, contributing to impactful publications and open-source projects.

Qualifications

• Requires a Master's degree in Computer Science or a related field with experience in LLM training, inference, or AI agent infrastructure.
• Preferred candidates have contributions to open-source projects like vLLM or publications in conferences such as OSDI or MLSys.

Responsibilities

• Develop and optimize key technologies for the AI infrastructure stack, including training, inference, and AI agents.
• Collaborate with academia and open-source communities to conduct research and publish academic papers.

Skills

LLM Training Infra

LLM Inference Infra

AI Agent Infra

GPU Kernel Optimization

Knowledge Distillation

RL Training

vLLM

SGLang

Cloud Infrastructure

Parallelism

AI Agents

Computer Science

Education

Master's degree in Computer Science or related field

Job description

ByteDance is seeking to develop and optimize core AI infrastructure technologies, covering training, inference, and AI agents. The role involves cutting-edge research collaboration with academia and open-source communities to advance the state of the art.

The position expects a strong foundation in computer science and hands-on experience with LLM tooling, contributing to impactful publications and open-source projects.