Software Engineer, Agents - Runpod

Runpod is pioneering the future of AI and machine learning, offering cutting-edge cloud infrastructure for full-stack AI applications. Founded in 2022, we are a rapidly growing, well-funded company with a remote-first organization spread globally. Our mission is to empower innovators and enterprises to unlock AI's true potential, driving technology and transforming industries. Join us as we shape the future of AI.

We believe AI agents will change how every team at RunPod works. We’re building them internally and expanding them externally to our customers. You’ll join a small, experienced team that has already shipped agents people use every day, and you’ll help make them more capable, more reliable, and more widely adopted across the company. The work spans agents that help people work with data and the shared tooling that lets more of RunPod build with AI. As these agents mature, we plan to bring what works to our customers, and you’ll have the chance to help shape and build those customer-facing experiences. This is a hands-on engineering role for someone who likes taking agents from promising to indispensable, and who cares as much about trust and accuracy as about capability.

Responsibilities

• Build, extend, and improve internal AI agents that help people across the business get work done faster, regardless of their technical background.
• Help take proven internal agents to customers, adapting them for external use with the reliability, security, and polish that customer-facing products require.
• Improve the accuracy, reliability, and explainability of agent outputs, so people can trust what they get back.
• Contribute to the shared tooling and infrastructure that make it easier and safer to build and run agents, both inside the company and for customers.
• Define and expand how we measure agent quality, including accuracy, latency, cost, and adoption, and build the evaluation practices that keep us honest.
• Harden agent systems for production, with strong attention to security, access controls, and observability.
• Work closely with your teammates and stakeholders across the company, including product, to find high-value use cases, gather feedback, and drive adoption.
• Keep up with the fast-moving agent ecosystem and help the team decide what’s worth adopting, what’s worth building, and what’s worth contributing back.

Requirements

• Hands-on experience building and shipping LLM-powered agents or applications in production, beyond prototypes.
• Strong software engineering skills in Python, and comfort working in and improving an existing codebase alongside other engineers.
• Solid SQL skills and familiarity with modern data tooling.
• Experience with core agent techniques, such as tool calling, retrieval, context management, and multi-step planning.
• Rigor in evaluating LLM systems, including building eval sets, catching regressions, and making trade-offs between quality, latency, and cost.
• A collaborative working style: you give and take code review well, share context generously, and can work with non-technical users to understand what they need.
• The ability to explain your results clearly in writing and turn them into decisions.

Preferred

• Experience shipping customer-facing AI products or features, including the guardrails, scale, and reliability work they need.
• Experience building internal tools or platforms used by multiple teams.
• Experience with agent frameworks, tool and connector protocols, or LLM observability tooling.
• Data engineering experience.
• Contributions to open-source AI or data projects.

Benefits & Compensation

• Competitive base pay ($100,000 - $130,000)
• Meaningful equity in a fast-growing AI infrastructure company (stock options)
• Generous medical, dental & vision plans
• Flexible PTO
• Remote-first work culture using Slack for communication
• $1,200 Home Office & Equipment Stipend