remoteonsite
Staff Software Engineer-AI - DigitalOcean
Software Engineer
Lead the design and delivery of AI inference services at scale, building managed agents, feedback loops, and cloud‑native infrastructure using Python, Go, Kubernetes, and modern ML tooling.
About the role
Key Responsibilities
- Architect, develop, and operate a high‑performance AI inference platform that serves millions of requests per day.
- Design and implement managed agent services that securely execute customer models in multi‑tenant environments.
- Build robust feedback and monitoring pipelines to continuously improve model performance and reliability.
- Collaborate with product, security, and infrastructure teams to define APIs, SLAs, and scaling strategies.
- Mentor senior engineers, drive best‑practice adoption, and champion a culture of code quality and automation.
Requirements
- 10+ years of software engineering experience, with a focus on large‑scale, cloud‑native systems.
- Deep expertise in Python and Go, and strong familiarity with container orchestration (Kubernetes) and containerization (Docker).
- Hands‑on experience building and deploying machine‑learning inference workloads in production.
- Proven track record designing distributed systems that handle high throughput and low latency.
- Excellent problem‑solving skills, ability to influence cross‑functional teams, and a passion for mentoring engineers.
Skills
pythongokubernetesdockermachine learning