Staff Software Engineer, Inference

Job overview

The Staff Software Engineer, Inference role is onsite in Sunnyvale, CA. The base salary range is $188,000–$275,000 per year. The role supports CoreWeave’s Inference Platform Team, which operates a Kubernetes-native platform for large-scale, low-latency AI workloads. As a technical leader, the engineer drives architecture, performance, and reliability across services and teams. The role improves inference systems through distributed-systems design, scheduling, batching, memory optimization, and GPU resource utilization.

What you'll do

• Lead cross-team design initiatives
• optimize inference latency, throughput, and GPU utilization
• improve system reliability at scale
• work on distributed systems and Kubernetes-based infrastructure, including scheduling, batching, and memory optimization
• influence engineering direction across the organization.

What we're looking for

Skills & competencies

staff software engineer

inference

sunnyvale ca

coreweave

ai infrastructure

kubernetes

distributed systems

gpu resource management

low-latency systems

high-throughput systems

go

python

c++

$188,000–$275,000/year

Work arrangement

• Weekend coverage required

Benefits & perks

• Medical, dental, and vision insurance fully paid by CoreWeave
• life and disability insurance
• flexible spending and health savings accounts
• tuition reimbursement
• employee stock purchase program
• mental wellness and family-forming support
• paid parental leave
• childcare support
• 401(k) with employer match
• flexible PTO
• and catered lunch at office and data center locations.

Why this role

Staff-level technical leadership across multiple services and teams; total rewards include discretionary bonus and equity awards, subject to eligibility.

About the employer

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