Staff Software Engineer: AI Inference Data Plane

digitalocean98 · San Francisco · $167k–$209k

Posted: 4 days ago
Last confirmed live: Today
Published range: $167k–$209k

What this role involves

This role involves designing and optimizing serverless AI inference infrastructure and APIs at DigitalOcean. Responsibilities include building scalable multi-tenant services, improving platform resiliency, and providing technical leadership. Candidates need 8+ years of experience in distributed systems, proficiency in Go and Kubernetes, and deep SRE and observability knowledge.

Skills this posting asks for

go
kubernetes
observability
sre
distributed systems
microservices
cloud-native
vllm
triton
api gateways
service mesh
tensorrt-llm
inference optimization
rate limiting
workload orchestration
ttft
tpot
gpu utilization
incident management
capacity planning
operational automation

Requirements

8 years of experience
Level: senior
Remote policy: remote

From the employer’s posting

Dive in and do the best work of your career at DigitalOcean. Journey alongside a strong community of top talent who are relentless in their drive to build the simplest scalable cloud. If you have a growth mindset, naturally like to think big and bold, and are energized…

Read the full description on digitalocean98’s careers page

Apply without filling the form

Approve this role and the application is completed for you, including a résumé tailored to it. You get a confirmation when it lands, and a credit is only spent when a submission is confirmed.

Claim 25 free applications

Other roles at digitalocean98

All 29 roles at digitalocean98 →