Staff Software Engineer, Inference

Tech Stack

Solid badges = required, outlined = preferred

Responsibilities

• Act as a technical leader driving architecture, performance, and reliability across multiple services and teams.
• Lead cross-team design initiatives and optimize inference performance (latency, throughput, and GPU utilization).
• Improve system reliability at scale, focusing on scheduling, batching, and memory optimization in distributed and Kubernetes-based infrastructure.
• Work hands-on, influencing engineering direction across the organization.
• Design and optimize high-performance distributed systems with a focus on AI inference and GPU systems.

Soft Skills

Benefits

• 401k
• Dental
• Disability Insurance
• Employee Stock Purchase
• Flexible PTO
• Flexible Spending Account
• Health Savings Account
• Life Insurance
• Medical
• Mental Health
• Parental Leave
• Tuition Reimbursement
• Vision

Culture

Requirements