SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 185,000 - 215,000 / annual
Pulumi is building Neo, an autonomous infrastructure engineering agent that acts as a virtual teammate for cloud operations. This role focuses on building the core systems that enable Neo to safely plan and execute multi-step infrastructure operations across AWS, Azure, GCP, Kubernetes, and other platforms.
Key responsibilities include designing and building the planning and execution systems that power Neo's autonomous operations, creating tool interfaces that give the agent semantic understanding of cloud resources, and developing context systems that help Neo understand customer infrastructure patterns. You'll build feedback loops and self-correction mechanisms to ensure reliable autonomous operation, create evaluation frameworks to measure agent performance across capabilities like migrations, compliance, cost optimization, and diagnostics, and develop the web interface where Neo operates as a virtual teammate with task assignment, progress visibility, and approval workflows.
Additional responsibilities include integrating Neo's capabilities into Pulumi's MCP Server for agent-to-agent workflows and collaborating with platform teams to deeply integrate agent capabilities into the CLI, SDKs, and Pulumi Cloud.
Ideal candidates are genuinely excited about agentic AI systems that plan, act, and adapt in the real world. You should have production experience building systems with LLMs, including skill design, tool use, function calling, and multi-step orchestration. You care deeply about reliability and safety when AI systems take real actions with real consequences, are comfortable across the full stack (agent orchestration, backend services, frontend interfaces), and have strong Python and TypeScript skills. A product mindset and ability to communicate clearly in a distributed team are essential.
Bonus experience includes cloud infrastructure knowledge (AWS, Azure, GCP), developer tools or platform engineering background, container orchestration familiarity, experience building evaluation frameworks for AI systems, and knowledge of prompt engineering, fine-tuning, MCP, or retrieval-augmented generation.
