CoreWeave
Software Engineer, Inference AI/ML
$92K–$135K
Sunnyvale, CA / Bellevue, WA +2 · Full-time · Posted Oct 24, 2025
- Location
- Sunnyvale, CA / Bellevue, WA
Bellevue, WA
Sunnyvale, California, United States - Education
- BS/MS in CS, EE, or related field, or equivalent practical experience.
- Visa sponsorship
- Requires access to export-controlled information; applicants must meet one of the stated U.S.-person, export-authorization-exemption, or export-authorization eligibility conditions. CoreWeave may decline to pursue export licensing for legitimate business reasons.
About the job
Implements and tests production features for model-serving services on CoreWeave’s GPU platform, focusing on inference latency, reliability, and cost.
What you'll do
- Implement well-scoped model-serving features and fixes; write tests, comments, and short design docs, and participate in code reviews.
- Add basic metrics and dashboards; assist with alarms and runbooks, and learn incident response through a guided on-call rotation.
- Contribute to guided performance experiments, such as request batching, concurrency, and caching.
What they ask for
- BS/MS in CS, EE, or a related field, or equivalent practical experience.
- Foundations in data structures, algorithms, and networked services.
- Experience with Python or Go; C++ is a plus.
- Linux fundamentals, Git/CI basics, and exposure to containers and Kubernetes.
Nice to have
- Internship or project deploying a microservice or ML inference demo.
- Coursework or research with PyTorch or TensorFlow; simple CUDA projects or familiarity with Grafana/Prometheus/OpenTelemetry or similar tooling.
Pay
USD 92,000 to USD 135,000 base salary
Tools
Python, Go, C++, Linux, Git, CI, Triton, vLLM
AI focus
Develops and optimizes GPU-based model inference and serving, including performance experiments involving batching, concurrency, and caching.
Model-written summary · the original posting is authoritative