Software Engineer, Applied AI

Cardinal Group Companies•Denver, CO

3h•$120,800 - $133,300

About The Position

The Software Engineer, Applied AI designs, builds, and supports production software and AI solutions that address business problems across Cardinal. Working across the full software development lifecycle, the engineer owns solutions end-to-end, including web applications, APIs, integrations, automated workflows, and AI agents. The role uses agentic development tools such as Claude Code and GitHub Copilot as everyday collaborators, applying software engineering and computer science fundamentals to direct, review, and verify AI-generated work so that delivered solutions are secure, tested, and maintainable. Working with a high degree of independence, the engineer moves quickly from prototype to production, partners with senior engineers on architecture, and helps raise the team's technical standards. The role also collaborates with business stakeholders and cross-functional partners, evaluates new AI models and tools, supports production operations, and contributes to Cardinal OKRs and training as needed.

Requirements

Bachelor's degree in Computer Science, Software Engineering, or a related technical field, or an equivalent combination of education and experience.
Three to five years of professional software engineering experience, including designing, building, and supporting production applications.
Strong computer science fundamentals in data structures, algorithms, and system design, plus software design skills in API design, data modeling, and design patterns, and the judgment to identify shortcomings in AI-generated code.
Proficiency in Python and TypeScript, with experience building RESTful APIs and front-end applications using modern frameworks.
Demonstrated daily use of agentic AI development tools, such as Claude Code, GitHub Copilot, or Cursor, including planning, directing, and verifying AI-generated work.
Experience building and shipping LLM-powered applications or AI agents, including tool calling, RAG, and prompt and context engineering.
Experience with automated testing, Git-based workflows, code review, and CI/CD pipelines.
Hands-on experience deploying and operating applications on a major cloud platform, including containers and serverless services.
Strong SQL skills and experience with relational databases.
Working knowledge of application security, including OAuth 2.0/OpenID Connect, secrets management, the OWASP Top 10, and LLM-specific risks such as prompt injection.
Ability to work independently through ambiguity, break problems into deliverable increments, and recognize when to involve senior team members.
Strong communication skills and the ability to explain technical decisions and trade-offs to technical and non-technical stakeholders.
A continuous-learning mindset and genuine curiosity about the rapidly evolving AI landscape.
Champion the Cardinal Culture and Cardinal Core Values every day.

Nice To Haves

FastAPI experience.
Angular experience.
Experience with Google ADK, LangGraph, or similar frameworks for LLM-powered applications or AI agents.
Experience with GitHub Actions.
GCP experience, including containers such as Docker and serverless services.
Experience with PostgreSQL.
Experience with BigQuery or another analytical data platform.
Familiarity with MCP, LLM evaluation and observability practices, and capability, cost, and latency trade-offs across model families such as Gemini, Claude, and OpenAI.
Experience with infrastructure-as-code such as Terraform, event-driven architectures, C#/.NET, Azure, or property management platforms such as Entrata.

Responsibilities

Translate business requirements into technical solutions, including web applications, APIs, integrations, automated workflows, and AI agents, and own delivery from prototypes through production releases.
Build backend services and RESTful APIs using Python and FastAPI, and front-end applications using TypeScript and Angular.
Use agentic development tools throughout planning, implementation, testing, and documentation; delegate scoped tasks to coding agents and rigorously review their results.
Build and maintain shared AI development assets, including agent instruction files, reusable skills and commands, and Model Context Protocol (MCP) servers.
Design, build, and operate AI agents and LLM-powered features using frameworks such as Google ADK or LangGraph, applying tool calling, retrieval-augmented generation (RAG), structured outputs, and multi-agent patterns where appropriate.
Build evaluation datasets and automated evaluations for AI features, instrument tracing and monitoring, and track production quality, cost, and latency.
Write and maintain unit, integration, and end-to-end tests and contribute to GitHub Actions CI/CD pipelines, including automated quality gates and AI-assisted code review.
Deploy and operate solutions on Google Cloud Platform, including Cloud Run, Cloud SQL, BigQuery, and Vertex AI; use containers and infrastructure-as-code where appropriate; and support production troubleshooting, root-cause analysis, and reliability improvements.
Design data models and integrations with internal and third-party systems using APIs, webhooks, and event-driven messaging, ensuring reliable data flows.
Apply secure-by-design practices, including authentication and authorization, secrets management, least-privilege access, protection of resident and team member data, and mitigation of AI-specific risks such as prompt injection.
Contribute to architecture and technical design discussions with senior engineers and document decisions and trade-offs.
Review human- and AI-authored code, contribute to team coding standards, and help mentor associate team members.
Collaborate with business stakeholders and cross-functional partners, including data engineering, to clarify requirements, demonstrate working software early, and communicate technical decisions accessibly.
Participate in sprint ceremonies, provide estimates, and surface technical risks and dependencies early.
Evaluate AI models, tools, and frameworks through proofs of concept and assess platform, framework, and model updates, including deprecations, for their impact on existing solutions.
Support Cardinal OKRs as needed.
Participate in Cardinal U training as required.