About Tavily
We're building the infrastructure layer for agentic web interaction at scale. Our API is designed from the ground up to power Retrieval-Augmented Generation (RAG) and real-time reasoning in AI systems. By connecting LLMs to high-quality, trustworthy web content, we help developers build agents that are not only intelligent — but also informed.
We work with some of the most innovative teams in AI — from small startups shaping the ecosystem to the largest enterprises deploying AI at scale. Whether it's powering sales assistants, research copilots, or internal knowledge tools, we're the missing link between LLMs and the real world.
The Role: DevOps Engineer
- Managing Kubernetes clusters across multiple environments and regions
- Owning infrastructure as code for all resources
- Maintaining and improving CI/CD pipelines and GitOps-based deployments
- Maintaining and optimize real-time data pipelines that process billions of events per day across distributed queues and stream processors
- Building out monitoring, alerting, and observability
- Debugging production issues across services
- Managing cloud costs and capacity planning
- Working closely with a small engineering team — you'd own infra, not a slice of it
What we're looking for
- ~3+ years in a DevOps or platform engineering role, working in production environments
- Proven experience designing and operating large-scale, distributed systems, with a solid understanding of API design, reliability, and performance at scale
- Strong Kubernetes experience in a managed cloud environment
- Proficiency with infrastructure as code (Terraform or similar)
- Experience with GitOps-based deployment workflows
- Built or maintained observability stacks (logging, metrics, alerting)
- Experience handling production incidents calmly and methodically
Nice to have:
- Multi-region deployments
- Search infrastructure
- Data pipeline experience (streaming, warehousing)
- Proxy/networking infrastructure at scale
Why Tavily?
- Full ownership — small team, you own the entire infrastructure, not a slice of it
- Real scaling challenges — bursty scraping workloads, cache invalidation, multi-region, millions of daily requests
- AI-native company — your infra directly powers AI agents used by leading companies in the space
- NYC-based — working closely with engineering, short feedback loops
