Software Engineer, Inference AI/ML

Job overview

The Software Engineer, Inference AI/ML role is onsite in Sunnyvale, CA. The base salary range is $92,000 to $135,000 per year. The engineer joins CoreWeave’s Inference team, which builds production features for model serving on its GPU platform. This early-career individual contributor role implements scoped changes and fixes that improve model-serving latency, reliability, and cost. The engineer contributes tests, documentation, metrics, dashboards, performance experiments, and guided operational learning to support dependable inference services.

What you'll do

• Implement features and fixes in Python, Go, or C++ for model-serving services
• write tests, code comments, and short design documents
• participate in code reviews
• add basic metrics and dashboards
• assist with alarms and runbooks
• follow on-call runbooks and learn incident response in a guided rotation
• contribute to performance experiments with guidance.

What we're looking for

Skills & competencies

software engineer

inference

ai/ml

model serving

gpu platform

python

go

c++

sunnyvale ca

coreweave

$92k–$135k/year

on-call rotation

Work arrangement

• Weekend coverage required

Benefits & perks

• Medical, dental, and vision insurance fully paid by CoreWeave
• life and disability insurance
• FSA and HSA
• tuition reimbursement
• employee stock purchase program
• mental wellness and family-forming support
• paid parental leave
• childcare support
• 401(k) match
• flexible PTO
• and catered office and data center lunches.

Why this role

The role includes mentorship and a guided incident-response rotation.

About the employer

CoreWeave is hiring for this role. Industry: Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services. Sector: 51.