Software Engineer - AI Inference for Science
Core
Engineer scalable AI inference solutions integrated within scientific workflows using HPC systems and AI accelerators.
Role type
Senior IC software engineer (AI inference)
Builds
Scalable inference services for scientific workflows
Domain
High-performance computing + AI for science
Deliverable
production ML models
Required skills
Python, C/C++, AI model deployment, vLLM or SGLang, REST API development, git, HPC systems, AI accelerators
Preferred skills
Distributed inference, HPC schedulers (Slurm, PBS), inference optimization, multi-user services, observability
Technologies
vLLM, SGLang, FastAPI, Slurm, PBS, Prometheus, Grafana
Responsibilities
Engineer solutions for AI inference via programmatic access and batch prompt processing; optimize inference performance on GPU/accelerator systems; integrate services with HPC schedulers; contribute to domain-specific software and models.
Seniority
Senior, hands-on IC
