Senior Software Engineer, Model Serving
Databricks is a data and AI platform that lets organizations build analytics, AI agents, and applications on a unified, governed lakehouse.
Funding history
Investors
About Databricks
Data engineers, analysts, and AI teams use Databricks to process large datasets, build reliable pipelines, and train models on a single governed platform. Users can run SQL analytics, serve ML predictions in real time, and deploy AI agents grounded in enterprise data. Its open lakehouse architecture provides consistent security and governance across analytical and operational workloads.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design and implement systems and APIs for scalable model serving. You will optimize inference performance, throughput, autoscaling, and operational efficiency across CPU and GPU workloads; improve deployment and runtime services; lead technical initiatives; and mentor engineers.
Requirements
- 5+ years of experience building and operating large-scale distributed systems
- Experience with model serving, inference systems, routing, scheduling, autoscaling, or observability
- Knowledge of algorithms, data structures, and system design for low-latency serving systems
- Experience building large-scale performance-sensitive CPU/GPU inference architectures
Responsibilities
- Design and implement core model serving systems and APIs
- Optimize performance, throughput, autoscaling, and operational efficiency for CPU and GPU workloads
- Build model container, deployment, routing, caching, observability, and autoscaling components
- Translate customer needs into reliable and performant systems
- Lead initiatives that improve latency, availability, and cost effectiveness
- Establish code quality, testing, and operational readiness practices
- Mentor engineers through design reviews and technical guidance
Benefits
- Eligibility for an annual performance bonus
- Equity