SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Stilta builds agentic AI software for intellectual property, enabling legal and IP teams to reason across massive document sets and produce litigation-grade work. The company recently raised a $10.5M seed round led by Andreessen Horowitz with participation from Y Combinator and operators from OpenAI, Legora, and Lovable. They work with major IP firms and Fortune 500 companies.
As Platform Engineer, you will own the infrastructure platform that powers every Stilta agent. Customers rely on long-running, document-heavy work with agents reasoning for hours across millions of pages. You'll be responsible for ensuring the infrastructure is fast, secure, and invisible to end users.
Key responsibilities:
- Design and operate the Kubernetes platform supporting large-scale agent swarms, including scheduling, autoscaling, and customer isolation
- Build systems that maintain agent session speed and resilience under heavy, unpredictable load
- Own infrastructure as code and production deployment on Azure, with enterprise-grade security, compliance, and data residency built in from the start
- Ensure storage and data pipelines are durable and performant for workloads spanning millions of documents
- Build observability systems that diagnose failures, not just alert to them
- Shape the scaling path from hundreds to thousands of concurrent agent sessions
- Set reliability and security standards that guide the engineering team for years
Requirements:
- Proven track record designing and scaling distributed systems in production with well-developed opinions on reliability
- Deep expertise in Kubernetes, cloud infrastructure, and infrastructure as code (Azure and Terraform experience preferred; equivalent depth elsewhere acceptable)
- Strong software engineering foundation in TypeScript and/or Python; comfortable building platform services, not just configuring them
- Treat reliability, performance, and cost as product decisions; instrument systems before troubleshooting
- Bonus: experience running AI or inference-heavy workloads at scale, or with enterprise security and compliance requirements
