SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Ivo builds AI products that help enterprises solve complex contracting problems using large language models. The company has achieved several infrastructure and product firsts, including AI agents embedded in MS Word, agentic RAG systems, large-scale LLM-based legal fact extraction, and advanced contract analysis capabilities.
As Senior Infrastructure Engineer, you will build and own the foundational systems that power Ivo's products. You'll work on multi-cluster, multi-region deployments across AWS/GCP/Azure with robust failover and disaster recovery. Key responsibilities include:
- Running and scaling Kubernetes clusters as a startup within the startup, managing isolated workloads for ML and API traffic with different performance and cost profiles
- Building internal tools for cluster creation and management to ensure consistency from development to production
- Designing security architecture (RBAC, workload identity, secrets management, data residency, audit trails) that is transparent to engineers but critical to operations
- Owning CI/CD pipelines using GitHub Actions and infrastructure-as-code with Pulumi
- Creating enforceable SLOs/SLIs that prevent false alarms while maintaining reliability
- Improving engineering velocity through faster builds, cleaner environments, and automation of repetitive tasks
- Owning observability and uptime, running incident response, and writing postmortems that drive learning
- Debugging across the full stack (frontend, backend, infrastructure) to identify and resolve issues systematically
This is not a "keep the lights on" role. You'll be deeply embedded in the engineering team and encouraged to push the frontiers of what's possible with LLMs and infrastructure.
Requirements:
- 5+ years of infrastructure/DevOps engineering experience
- Deep Kubernetes expertise (not just deployment-level knowledge)
- Proficiency with infrastructure-as-code (Pulumi or Terraform) and CI/CD (GitHub Actions, Docker)
- Demonstrated experience with multi-cluster, multi-region setups
- Strong debugging skills and systematic root-cause analysis
- Understanding of how compliance and legal requirements translate into engineering constraints
- Full-stack range sufficient to avoid getting stuck on any layer
- Startup experience preferred but not required
- Traits: relentlessly resourceful, strong internal sense of urgency, bias toward action, excited about building a company
