Senior Engineer II — Serverless AI Inference (Hybrid)

DigitalOcean; Seattle (WA); Hybrid; USD 167,000 - 209,000; Full time

Benefits offered by this job

Equity compensation

Bonus potential

Job summary

DigitalOcean is seeking a Senior Engineer II to design and optimize serverless inference infrastructure and APIs for high-throughput AI workloads. You will enhance observability, reliability, and capacity planning while collaborating with platform, GPU, and product teams to deliver production-grade systems and highly available APIs.

The role requires 7+ years building distributed backend systems, 1+ year Go in production, and 2+ years Kubernetes experience, with a focus on on-call readiness and

Qualifications

• 7+ years building and operating multi-tenant platforms or distributed backend systems.
• Strong production experience with high-scale distributed services.
• Deep understanding of SRE: observability, incident management, reliability, capacity planning, automation.
• 1+ years hands-on Go in production.
• 2+ years Kubernetes experience.
• Cloud-native architectures, microservices, distributed systems fundamentals.
• Experience debugging performance, scalability, reliability in production.
• Observability proficiency: TTFT, TPOT, GPU utilization metrics.

Responsibilities

• Design and build scalable, multi-tenant services powering AI inference and routing workloads.
• Improve resiliency via observability, capacity, automation, and tooling.
• Collaborate with platform, GPU infra, and product teams for production-grade systems and APIs.
• Raise engineering bar with solid design, incident management, and continuous improvement.
• Contribute to traffic management, service orchestration, reliability, and platform scalability.
• Participate in on-call rotations and reduce operator pain and incidents.
• Provide technical leadership by breaking down complex problems and guiding execution.
• Mentor junior/mid engineers through coaching and pairing.

Skills

Go/Golang

Kubernetes

SRE principles

Observability

Distributed backend

Multi-tenant

Incident management

Performance debugging

Job description

DigitalOcean is seeking a Senior Engineer II to design and optimize serverless inference infrastructure and APIs for high-throughput AI workloads. You will enhance observability, reliability, and capacity planning while collaborating with platform, GPU, and product teams to deliver production-grade systems and highly available APIs.

The role requires 7+ years building distributed backend systems, 1+ year Go in production, and 2+ years Kubernetes experience, with a focus on on-call readiness and