Senior Software Engineer, Agentic AI

pulumicorporation; United States; Remote; USD 185,000 - 215,000; Full time

Benefits offered by this job

Remote-friendly US

Salary range $185k–$215k

Medical, dental, vision insurance

Unlimited PTO with minimum 3 weeks

401(k) with match

Parental leave (20/16 weeks)

Learning & development budget

Wellness fund

Work-from-anywhere stipend

Job summary

Pulumi Corporation is seeking a senior engineer to join a remote-first US team building an autonomous infrastructure engineering agent that plans and executes multi-step cloud operations. You will work across the stack from orchestration to the web experience, shipping reliable systems where AI takes real-world actions.

You will design planning and execution systems for AWS, Azure, GCP, Kubernetes, and related platforms, develop safety loops, and contribute to CLIs, SDKs, and platform services.

Qualifications

• Proven production experience with large language models, including tool use, function calling and multi-step orchestration.
• Strong care for reliability and safety when AI systems take consequential actions on real infrastructure.
• Comfort across full stack from agent orchestration to frontend interfaces.

Responsibilities

• Build planning and execution systems for multi-step infrastructure operations across AWS, Azure, GCP, Kubernetes, and related platforms.
• Design tool interfaces and semantic models for deep understanding of cloud resources and workflows.
• Develop context systems capturing customer infrastructure patterns and usage over time.
• Create feedback loops and self-correction mechanisms for reliable autonomous operations with real-world consequences.
• Build evaluation frameworks measuring performance in migrations, compliance, cost optimization, and diagnostics.
• Shape the web interface and integrate capabilities into CLIs, SDKs, and platform services.

Skills

Python

TypeScript

LLM tooling

Reliability engineering

Safety in AI

Distributed systems

Frontend interfaces

Tools

Kubernetes

Docker

Infrastructure as Code

Job description

Role overview

The team is building an autonomous infrastructure engineering agent that plans and executes multi-step cloud operations, acting as a virtual teammate for engineers, developers, and security practitioners. The work spans the full stack of an agentic AI product, from orchestration logic and tool design to the web experience where users observe progress, approve actions, and inspect reasoning. This is a senior engineering role on a remote-first U.S. team, with an emphasis on shipping reliable systems where AI takes real-world actions.

Responsibilities

• Build planning and execution systems that let the agent safely perform multi-step infrastructure operations across AWS, Azure, GCP, Kubernetes, and related platforms
• Design tool interfaces and semantic models that give the agent deep understanding of cloud resources and engineering workflows
• Develop context systems that capture each customer's infrastructure patterns, conventions, and usage over time
• Create feedback loops and self-correction mechanisms so autonomous operation stays reliable when actions have real consequences
• Build evaluation frameworks measuring performance across capability areas such as migrations, compliance, cost optimization, and diagnostics
• Shape the web interface where users assign tasks, watch the agent work, and approve operations, plus integrate capabilities into CLIs, SDKs, and platform services

Requirements

• Genuine enthusiasm for agentic AI: systems that plan, act, and adapt in the real world rather than only generate text
• Production experience building with large language models, including skill design, tool use, function calling, and multi-step orchestration
• Strong care for reliability and safety when AI systems take consequential actions on real infrastructure
• Comfort working across the stack, from agent orchestration and backend services to frontend interfaces
• Solid Python and TypeScript skills, with the ability to ramp quickly in new environments
• A product mindset that centers user needs, plus clear communication in a distributed team

Nice to have

• Hands-on experience with AWS, Azure, or GCP, or with infrastructure-as-code tooling
• Background in developer tools, CLIs, or platform engineering systems
• Familiarity with Kubernetes, Docker, or related container orchestration
• Experience designing evaluation frameworks or benchmarks for AI systems
• Knowledge of prompt engineering, fine-tuning, model context protocols, or retrieval-augmented generation

Benefits and work setup

• Remote-first within the U.S., with a preference for candidates in Pacific Time Zone locations
• Base salary range of $185,000 to $215,000, plus variable compensation and equity
• Comprehensive medical, dental, vision, and supplemental insurance at no cost to U.S. employees
• Unlimited paid time off with a requirement to take at least three weeks annually, plus 13 U.S. holidays
• 401(k) plan with employer match and paid parental leave of 20 weeks for primary caregivers and 16 weeks for secondary caregivers
• Annual learning and development budget, monthly wellness fund, quarterly team connection fund, and an annual work-from-anywhere stipend