CareerPlanGet AI match score →

Staff Software Engineer, Foundational Model Serving

Mountain View, California💼 Full-time💰 $192,000–$192,000🗓 2026-04-09 → 2026-07-31

Core

Design and build high-throughput, low-latency inference systems for hosting and serving frontier AI models (open source and proprietary) via API.

Role type

Staff Software Engineer (Foundational Model Serving)

Builds

Foundation Model Serving API product for hosting and serving frontier AI model inference

Domain

AI Infrastructure / Large Language Model Serving

Deliverable

production ML models

Required skills

large-scale distributed systems, high-scale operationally sensitive backend systems, system design, algorithms, data structures, GPU workload optimization, vLLM, SGLang, token-based rate limiting, architectural trade-offs, code quality, testing, operational readiness, technical mentorship

Preferred skills

product-oriented mindset, cross-functional collaboration, strategic vision

Technologies

vLLM, SGLang, GPU workloads

Responsibilities

Design and implement core systems and APIs ensuring scalability and reliability; Define technical roadmap and long-term architecture; Optimize performance, throughput, and autoscaling for GPU serving workloads; Contribute to key infrastructure components like rate limiters and optimizers; Collaborate cross-functionally to translate customer needs into performant systems; Establish best practices for code quality and mentor engineers; Represent the team in cross-organizational technical discussions

Seniority

Staff, hands-on IC with strategic influence

Rewrite
## Responsibilities - Design and implement core systems and APIs that power Databricks Foundation Model Serving, ensuring scalability, reliability, and operational excellence. - Partner with product and engineering leadership to define the technical roadmap and long-term architecture for serving workloads. - Drive architectural decisions and trade-offs to optimize performance, throughput, autoscaling, and operational efficiency for GPU serving workloads. - Contribute directly to key components across the serving infrastructure — from working in systems like vLLM and SGLang to creating token based rate limiters and optimizers — ensuring smooth and efficient operations at scale. - Collaborate cross-functionally with product, platform, and research teams to translate customer needs into reliable and performant systems. - Establish best practices for code quality, testing, and operational readiness, and mentor other engineers through design reviews and technical guidance. - Represent the team in cross-organizational technical discussions and influence Databricks’ broader AI platform strategy. ## Requirements - 10+ years of experience building and operating large-scale distributed systems. - Experience leading high-scale operationally sensitive backend systems. - A track record of up-leveling teams engineering excellence. - Strong foundation in algorithms, data structures, and system design as applied to large-scale, low-latency serving systems. - Proven ability to deliver technically complex, high-impact initiatives that create measurable customer or business value. - Strong communication skills and ability to collaborate across teams in fast-moving environments. - Strategic and product-oriented mindset with the ability to align technical execution with long-term vision. - Passion for mentoring, growing engineers, and fostering technical excellence. ## Nice to Have - Prior ML or AI experience. ## Benefits - Competitive salary and benefits package. - Opportunities to work on cutting-edge AI infrastructure. - Collaborative and innovative work environment.
Sourced via greenhouse · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
Apply on Greenhouse ↗