Staff Backend Engineer, AI Model Serving

Neura Market; San Francisco, Northern (CA, KY); Hybrid; USD 192,000 - 260,000; Full time

Job summary

Databricks is seeking a Staff Engineer for its Model Serving team in San Francisco. You will design and build core systems for high-throughput, low-latency inference across CPU and GPU workloads, shaping roadmaps and collaborating with platform, product, infrastructure, and research teams to deliver a world-class serving platform.

You will mentor engineers, drive architectural decisions, and establish best practices for code quality, testing, and operational readiness, contributing to latency,

Qualifications

• 10+ years of experience building and operating large-scale distributed systems.
• Deep expertise in model serving, inference systems, and related infrastructure.
• Strong foundation in algorithms, data structures, and system design for low-latency serving.

Responsibilities

• Design and implement core systems and APIs powering Databricks Model Serving.
• Partner with leadership to define the technical roadmap for serving workloads.
• Drive architectural decisions to optimize performance, throughput, and autoscaling.
• Mentor engineers through reviews and guidance.
• Collaborate across product, platform, and research teams to translate customer needs into reliable systems.

Skills

Distributed systems

Model serving

Algorithms & data structures

Low-latency

Leadership/mentoring

Communication

Job description

Databricks is seeking a Staff Engineer for its Model Serving team in San Francisco. You will design and build core systems for high-throughput, low-latency inference across CPU and GPU workloads, shaping roadmaps and collaborating with platform, product, infrastructure, and research teams to deliver a world-class serving platform.

You will mentor engineers, drive architectural decisions, and establish best practices for code quality, testing, and operational readiness, contributing to latency,