Software Engineer - AI Inference for Science

About the role

The Argonne Leadership Computing Facility (ALCF) accelerates major scientific discoveries by providing world‑leading computing resources and expertise. The Data Services and Workflows group seeks a Software Engineer to enable AI for science, focusing on scalable inference on HPC systems and AI accelerators. The role involves integrating AI inference into scientific workflows, collaborating with application teams, academia, industry, and other national labs, and contributing to broader scientific initiatives.

Responsibilities

• Explore and engineer solutions for AI inference integrated within scientific workflows via programmatic access (e.g., OpenAI API) and large‑batch prompt submission for parallel processing.
• Ensure efficient execution on ALCF’s HPC systems and AI testbed machines, understanding AI model compute and memory requirements.
• Adapt and deploy new AI models and functionality as the field evolves.
• Work collaboratively with science application teams, academia, industry, and other national labs to solve complex scientific and engineering problems.
• Contribute to broader scientific initiatives and support domain‑specific software and models.

Requirements

• Overall familiarity with AI model use, deployment, and memory‑ and compute‑requirements.
• Familiarity with one or more AI hosting frameworks such as vLLM or SGLang.
• Familiarity with REST API development in Python using frameworks such as FastAPI.
• Comprehensive experience programming in one or more languages such as Python, C/C++.
• Ability to create, maintain, and support high‑quality software.
• Experience with version control software such as git.
• Ability to work collaboratively in a fast‑paced environment.
• Effective written and oral communication skills.
• Ability to model Argonne’s core values of impact, safety, respect, integrity, and teamwork.

Qualifications

• RD2 level: Bachelor’s degree and 5+ years experience, Master’s degree and 3+ years experience, or PhD (or equivalent). Expected pay range: $94,486 – $147,399.
• RD3 level: Bachelor’s degree and 8+ years experience, Master’s degree and 5+ years experience, or PhD and 4+ years experience (or equivalent). Expected pay range: $116,250 – $181,350.

Skills (Preferred)

• Experience designing or operating distributed inference or data services (request routing, asynchronous execution, queueing, fault tolerance, performance monitoring).
• Experience integrating services with HPC schedulers (Slurm, PBS), including resource provisioning, job lifecycle management, and balancing latency‑sensitive and throughput‑oriented workloads.
• Experience optimizing AI inference performance (batching, memory management, model parallelism, quantization, accelerator utilization) on GPU‑ or accelerator‑based systems.
• Familiarity with secure, multi‑user services (authentication/authorization, API security) in institutional or regulated environments.
• Experience with log aggregation, analytics, and observability (Prometheus, Grafana, log aggregators, OLAP or data warehousing techniques).

Benefits

Comprehensive benefits are part of the total rewards package; details are available via the Argonne employee benefits page.

Pay

The expected hiring range for this position is $94,486.00 – $147,398.94. Actual pay will be based on the scope and responsibilities, candidate qualifications, business considerations, internal equity, and external market pay for comparable jobs.

Schedule

This position qualifies as “Hybrid Remote Work – Occasionally Onsite”: employees typically work more than 60% of their time remotely with a mix of onsite and remote days. The role is regular, full‑time.