AI Inference Engineer for Scientific HPC

Argonne; Chicago (IL); Hybrid; USD 94,000 - 181,000; Full time

Benefits offered by this job

Comprehensive benefits

Job summary

Argonne National Laboratory's Leadership Computing Facility (ALCF) seeks a Software Engineer to advance AI for science by enabling scalable inference on HPC systems and accelerators. You will integrate AI models into scientific workflows and expose programmatic access via interfaces like REST/OpenAI API, collaborating across science applications and external partners.

The role is hybrid with onsite and remote days, requires strong Python/C/C++, experience with AI hosting frameworks

Qualifications

• Familiarity with AI hosting frameworks such as vLLM or SGLang.
• Experience with REST API development in Python (FastAPI).
• Proficient in Python and C/C++ programming.
• Strong teamwork and effective communication.

Responsibilities

• Develop scalable AI inference within scientific workflows.
• Interface with HPC resources and AI accelerators.
• Collaborate with science applications teams and external partners.

Skills

Python

C/C++

REST API

Git

Collaborative work

Education

Bachelor's degree

Tools

vLLM

SGLang

FastAPI

Slurm

PBS

GPU accelerators

Job description

Argonne National Laboratory's Leadership Computing Facility (ALCF) seeks a Software Engineer to advance AI for science by enabling scalable inference on HPC systems and accelerators. You will integrate AI models into scientific workflows and expose programmatic access via interfaces like REST/OpenAI API, collaborating across science applications and external partners.

The role is hybrid with onsite and remote days, requires strong Python/C/C++, experience with AI hosting frameworks