DigitalOcean's Agentic Inference Cloud delivers predictable cost efficiency, radically simple operations and high performance at scale - so teams can focus on building AI products instead of managing infrastructure or absorbing surprise costs. The platform combines production-ready GPU infrastructure, a full-stack cloud, model-first inference workflows, and an agentic experience layer to reduce operational complexity and accelerate time to production. More than 640,000 customers trust DigitalOcean to deliver the cloud and AI infrastructure they need to build and grow.
Dive in and start the most exciting chapter of your career at DigitalOcean. Journey alongside a community of top talent relentless in their drive to build the Agentic Inference Cloud. We are looking for Software Engineers to help us build a developer-first, vertically integrated platform that simplifies the entire AI lifecycle.
Our engineering team owns this stack end-to-end. You will work on everything from low-level kernel and GPU optimizations to high-performance dedicated clusters and serverless APIs. By engineering every layer of the infrastructure, we ensure that state-of-the-art models - across LLMs, image, audio, and video - run at peak efficiency on a global scale.
You must be currently located in and able to work 3 days per week in the DigitalOcean office we are building in Seattle.
What You'll Do- Feature Development: Write production grade Go and Python to solve the "unit economics" of AI- optimizing how we monetize a single GPU across multiple abstraction layers.
- Performance Engineering: Implement and experiment with prefix caching, batch inferencing, and model quantization to reduce TCO for our customers.
- Model Integration: Assist in the development of model catalogs and automated benchmarking tools to help customers move their models from experimentation to production.
- Operational Excellence: Help manage a global GPU footprint, ensuring 99.9% uptime for mission-critical production workloads.
- Continuous Learning: Collaborate with senior engineers to learn complex system architectures and contribute to high-density GPU orchestration.
What You'll Add to DigitalOcean- Foundational Knowledge: 1-3 years of software engineering experience with an interest in ML platforms, AI techniques (e.g., LLMs, multimodal, large vision models), or GenAI-related concepts.
- Technical Proficiency: Solid understanding of at least one backend language (Python or Go preferred) and experience working with REST APIs.
- Problem Solving: A proactive approach to troubleshooting and a desire to build production-grade systems in a high-growth tech environment.
- Collaboration: Strong communication skills and a team-first mindset, with the ability to take feedback and apply it to code improvements.
- Tooling Curiosity: Familiarity with containerization (Docker/Kubernetes) and cloud infrastructure is a plus.
Compensation Range: *This is a hybrid role
#LI-Hybrid
