Cloud Computing

Staff Engineer, Serverless Inference

Seattle, WAHybridFull TimeSenior$191,200–$239,000 /yrPosted 1 month agoVisa sponsorship available

Is this role right for you?

Upload your resume and get a skill-by-skill breakdown — see exactly where you match, where you're close, and what to highlight. Not a mystery percentage.

Get a tailored resume highlighting what this role needs.

Required skills

Serverless Inference
multi-tenant services
AI workloads
GPU utilization
fault tolerance
highly available APIs
software design
operational discipline
continuous improvement
architecture decisions

Nice to have

LLM serving architectures
vLLM
Triton
API gateways
traffic routing
service mesh

Role summary

Seeking a Senior Engineer II to design, implement, and optimize Serverless Inference infrastructure and APIs for large-scale AI workloads. Responsibilities include building scalable, multi-tenant services, enhancing platform resiliency through observability and automation, and contributing to architecture decisions. The role requires strong software design, operational discipline, and incident management skills. Candidates should have 7+ years of experience with distributed systems, 1+ years with Go, and 2+ years with Kubernetes. Experience with SRE principles, performance debugging, and observability metrics is essential. Familiarity with LLM serving architectures and API gateways is a plus. This is a hybrid role with a compensation range of $167,000 - $209,000.

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 by the fast-paced environment of a true industry disruptor, you’ll find your place here. We value winning together—while learning, having fun, and making a profound difference for the dreamers and builders in the world.

We are seeking a Staff Engineer to implement and contribute to the design and optimization of our Serverless Inference infrastructure and APIs. In this role, you will tackle the challenges of large-scale AI workloads, focusing on throughput, GPU utilization, and fault tolerance to support next-generation inference needs of AI native enterprises.

What You'll Do:

Design and build scalable, multi-tenant services that power AI inference and intelligent routing workloads.

Strengthen platform resiliency through improved observability, capacity management, automation, and operational tooling.

Partner closely with platform, GPU infrastructure, and product engineering teams to deliver production-grade systems and highly available APIs.

Raise the engineering bar through strong software design, operational discipline, incident management, and continuous improvement practices.

Contribute to architecture decisions around traffic management, service orchestration, reliability, and platform scalability.

Participate in on-call rotations and lead efforts to reduce operator pain, improve service health, and prevent recurring incidents.

Provide technical leadership on projects by breaking down ambiguous problems and guiding engineers toward clear execution plans.

Support the growth of junior and mid-level engineers through coaching, pairing, and constructive feedback.

Foster a culture of ownership, accountability, and continuous learning across the team.

Lead by example in incident response, operational readiness, and production-quality engineering practices.

What You'll Bring:

Required

7+ years of experience building and operating multi-tenant platforms or distributed backend systems

Strong experience operating high-scale distributed services in production environments

Deep understanding of SRE principles, including observability, incident management, reliability engineering, capacity planning, and operational automation

1+ years of hands-on experience with Go / Golang in production systems

2+ years of experience with Kubernetes

Strong understanding of cloud-native architectures, microservices, and distributed systems fundamentals

Experience debugging performance, scalability, and reliability issues in production systems

Observability Proficiency: Experience tracking infrastructure and inference metrics like Time To First Token (TTFT), Time Per Output Token (TPOT), and GPU utilization.

Bonus

AI/ML Framework Knowledge: Understanding of modern LLM serving architectures and familiarity with engines like vLLM or Triton.

Experience with API gateways, traffic routing, or service mesh technologies

Familiarity with LLM serving stacks such as vLLM, TensorRT-LLM, or similar technologies

Experience building systems for inference optimization, rate limiting, routing, or workload orchestration

Compensation Range:

$191,200 - $239,000

*This is a hybrid role

JR: 2026-8187

#LI-Hybrid

Why You’ll Like Working for DigitalOcean

We innovate with purpose. You’ll be a part of a cutting-edge technology company with a high-growth trajectory, who are proud to simplify cloud and AI so builders can spend more time creating software that changes the world. As part of our team, you’ll embody our "Shark" mindset: bold, ambitious, and scrappy. You'll lead with a bias for action and take true ownership of our products, customer success, and team culture.

We prioritize career development. At DigitalOcean, you’ll do the best work of your career. You will join a community of exceptional talent, collaborating closely with some of the brightest and most interesting people in the industry. We are a high-performance and fast-paced organization that will always challenge you to think big. Our talent development team prioritizes your professional development and provides resources to support your growth. We provide employees with reimbursement for relevant conferences, training, and education, subject to company policy.

We care about your well-being. We take a comprehensive approach to our total rewards packages because we know different things drive different people. Our benefits are designed to support you and may include flexible time off, local team meetups, and mental health and well being support. Our benefits philosophy is consistent globally, but specific benefits and eligibility vary by location to reflect local needs and regulations.

We reward our employees. The salary range for this position is based on market data, relevant years of experience, and skills. Eligible employees may also receive equity compensation, which may include a new hire equity grant and, in participating countries, the opportunity to participate in our Employee Stock Purchase Program. Equity awards are subject to approval and the terms of the applicable plan.

Non-sales roles: In addition to base salary, this role is eligible to participate in DigitalOcean’s annual bonus plan and may be eligible for a new hire equity grant, subject to plan terms and local eligibility. Bonus amounts depend on company and individual performance.

Sales roles (sales compensation eligible): In addition to base salary, this role may be eligible to earn incentive compensation under the applicable sales compensation plan and may be eligible for a new hire equity grant, subject to plan terms and local eligibility.

DigitalOcean is an equal-opportunity employer. We do not discriminate on the basis of race, sex, disability, protected veteran status, or any other characteristic protected by applicable law.

Application Limit: You may apply to a maximum of 3 positions within any 180-day period. This policy promotes better role-candidate matching and encourages thoughtful applications where your qualifications align most strongly.

Sample DigitalOcean interview questions

1
Design a system for managing a distributed chaos engineering platform.
system designmedium
2
Design a system for real-time monitoring of cloud infrastructure.
system designmedium
3
Architect a real-time document collaboration tool.
system designmedium
4
Build a system for recognizing faces in real-time with high accuracy.
system designmedium
5
Longest Consecutive Sequence Determine the length of the longest consecutive elements sequence. Input: nums = [0,3,7,2,5,8,4,6,0,1] Output: 9 Explanation: The longest consecutive sequence is 0 through 8 (length 9), utilizing a hash set to check connectivity in linear time.
technicalmedium

Get started to unlock a personalized interview prep pack for this role.

Ready to apply?

You'll be redirected to DigitalOcean's application page.