Senior Software Engineer - Iris AI

About Delinea: Delinea is a pioneer in securing human and machine identities through intelligent, centralized authorization, empowering organizations to seamlessly govern their interactions across the modern enterprise. Leveraging AI-powered intelligence, Delinea’s leading cloud-native Identity Security Platform applies context throughout the entire identity lifecycle – across cloud and traditional infrastructure, data, SaaS applications, and AI. It is the only platform that enables you to discover all identities – including workforce, IT administrator, developers, and machines – assign appropriate access levels, detect irregularities, and respond to threats in real-time. With deployment in weeks, not months, 90% fewer resources to manage than the nearest competitor, and a 99.995% uptime, Delinea delivers robust security and operational efficiency without compromise. Learn more about Delinea on Delinea.com , LinkedIn , X , and YouTube .

Join our passionate, global team at Delinea and help us make the world a safer and more secure place. Our success is driven by world-class product leadership, outstanding engineers, and strategic investment from TPG. We value diversity, innovation, and a culture of respect and fairness. If you're ready to push boundaries and challenge the status quo in security, we want to hear from you.

Apply today to help us achieve our mission.

About the Iris AI Team:

Iris AI is the team building the AI-powered capabilities of the Delinea Platform. We put LLMs to work on real security problems: detecting anomalies in audit data, making authorization decisions smarter, and building agents that do real work for our customers. The problems are new, the pace is fast, and what you build ships to some of the world's largest organizations.

Summary:

You'll design, build, and run the cloud services behind Delinea's AI features, with LLMs as part of your toolkit: inference, retrieval, agents, and evaluation are all product surface you own. Our services are written in C#/.NET, Python, and Go. Be strong in one, and be willing to work in any. You'll report to the Director of Engineering, Iris AI.

What You'll Do:

• Build and run scalable, highly available backend services in C#/.NET, Python, and Go on Azure and Kubernetes.

• Build LLM-powered features on platforms like Azure AI Foundry: model integration, context pipelines, RAG, tool calling, agents, and evals.

• Design event-driven, asynchronous architectures across our microservices.

• Own delivery end to end: Terraform, CI/CD, monitoring, and production incident response.

• Work closely with product, UX, and other platform teams; give and get sharp code and design reviews.

• Build with AI every day. We use coding agents to design, write, and review code, and we hold that code to the same bar as anything written by hand.

What You'll Need:

• A degree in Computer Science or a related field, or equivalent experience.

• 8+ years designing and building production backend services in C#/.NET, Python, or Go, with experience across the full software development lifecycle.

• Hands-on experience building products with LLMs (not just using them): inference, structured outputs, RAG, tool calling, or agents on Azure AI Foundry, the OpenAI API, Amazon Bedrock, Google Vertex AI, the Anthropic API, or similar.

• Fluency with AI-assisted development (Claude Code, GitHub Copilot, Cursor) treated as a discipline in its own right: spec-driven development, careful context, and verified, tested output.

• Strong grasp of distributed systems, API design, and microservices, plus experience with a major cloud provider.

• Solid understanding of multi-tenant SaaS architecture and the trade-offs of operating at scale.

We'd Love to See:

• Experience building tools, APIs, or integrations that AI agents call - MCP servers, function/tool-calling interfaces, plugins, or similar.

• ML and MLOps depth: fine-tuning, eval harnesses, and deploying and evaluating models in production.