Distributed LLM Inference Engineer

Intel Corporation

Prescott (AZ)

On-site

USD 52,000 - 82,000

Full time

11 days ago

Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Job summary

Intel Corporation in Shanghai is hiring a College Grad Software Engineer to contribute to distributed LLM inference systems within the AI Frameworks team. You will design, implement, and optimize components for high-performance AI software on diverse hardware, collaborating with researchers and engineers to push AI capabilities forward.

The role emphasizes distributed algorithms, model/data parallelism, and efficient communication, with a strong foundation in Python and C++ and knowledge of

Qualifications

Master’s degree or higher in Computer Science, AI, or related field.
Proficiency in Python and modern C++ programming.
Foundational knowledge of deep learning frameworks (e.g., PyTorch).
Experience debugging and optimizing software for performance.
Strong problem-solving and quick learning of unfamiliar systems.

Responsibilities

Design, develop, and optimize distributed LLM inference systems and AI framework components.
Implement distributed algorithms and asynchronous communication for deep learning.
Develop components like schedulers, workers, and KV cache management.
Profile workloads to identify bottlenecks in compute, communication, memory, and scheduling.
Collaborate with teams to improve latency, throughput, and scalability.

Skills

Python

C++

PyTorch

Distributed systems

Performance optimization

Education

Master’s degree in CS/AI/Software Engineering

Tools

Git

Job description

The role emphasizes distributed algorithms, model/data parallelism, and efficient communication, with a strong foundation in Python and C++ and knowledge of

Get your free, confidential resume review.

or drag and drop your file here.