> Markdown version of [/jobs/ext/585162-senior-software-engineer-applied-ai](https://www.wearedevelopers.com/jobs/ext/585162-senior-software-engineer-applied-ai). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior Software Engineer, Applied AI - **Company:** Cato Institute - **Location:** Washington, DC, United States - **Experience:** Expert - **Salary:** $100,000.0 - $190,000.0 - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Code Review, Continuous Integration, Programming Tools, Python (Programming Language), Software Engineering, Data Streaming, TypeScript, Data Logging, Data Processing, ReactJS, Retrieval-Augmented Generation, Large Language Models, Prompt Engineering, Codebase, Front End Software Development, GPT, Software Version Control, Data Pipelines - **Published:** June 18, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=1043c7d89a5b32a8 ## About the Role Do you have experience in Version control systems?, Do you have a Bachelor's degree?, * Bachelor's degree in any field * 5+ years of professional software engineering experience, including work on production systems * Expertise with multiple major LLMs: Claude, ChatGPT, and/or Gemini * Expertise with agentic AI development tools (Claude Code, Codex, or similar), including authoring reusable agent capabilities - agent skills, structured workflows, and tool integrations - not just using them * Proficiency in TypeScript / React or Python, with demonstrated ability to work productively in languages and frameworks outside your primary expertise * Experience building or integrating LLM-enabled systems - prompt engineering, retrieval-augmented generation, tool use, or evaluation pipelines, * Strong software engineering fundamentals: testing, version control, CI/CD, code review, and systems design * Comfort working across the stack - backend services, frontend components, data pipelines, and build infrastructure * Clear written and verbal communication; ability to document systems and explain technical decisions to non-engineers * Self-directed, adaptable, and comfortable with ambiguity in a small team where priorities shift * Familiarity with Cato's work or demonstrated interest in public policy, * Familiarity with headless CMS platforms, content modeling, or structured content systems * Experience building streaming or pipeline-based data processing systems * Experience with AI output evaluation frameworks or quality benchmarking tools * Experience authoring and maintaining agent skills (such as Claude/Claude Code Skills) or comparable agentic workflow packages * Familiarity with think tank, research, government, or academic technology environments, Applicants must be currently authorized to work in the United States on a full-time basis. This position does not offer visa sponsorship. ## Description * Build and maintain sophisticated agent skills and agentic tooling that integrate AI across engineering and operational workflows * Integrate AI content retrieval systems, such as Sanity's Agent Context, into production workflows * Build services (e.g., API and MCP endpoints) that surface Cato's 50 years of policy research for diverse consuming applications * Build and extend features, components, and shared packages across both the TypeScript / React content platform and the Python research and operations platform * Extend and harden core infrastructure packages across both platforms: API client integration, streaming data pipelines, document processing, and structured logging * Maintain testing infrastructure across both platforms, closing coverage gaps and integrating tests into continuous integration workflows Likely Initial Focus Areas (First 6 - 12 Months) * Contribute to the content platform's march toward production, picking up feature work, migration tasks, and building pipeline improvements * Develop familiarity with both codebases through Cato's AI development infrastructure - project instruction files, quality enforcement hooks, and structured reasoning frameworks that provide persistent architectural context and catch errors in real time * Build out test suites for both platforms, prioritizing high-dependency packages and critical paths ## Related Videos - [Getting to Know Your Legacy (System) with AI-Driven Software Archeology](https://www.wearedevelopers.com/videos/1437-getting-to-know-your-legacy-system-with-ai-driven-software-archeology) - [Watch Tests Go Brrrr! : Getting Started with Cypress in ReactJS](https://www.wearedevelopers.com/videos/282-watch-tests-go-brrrr-getting-started-with-cypress-in-reactjs) - [ Evaluating AI models for code comprehension](https://www.wearedevelopers.com/videos/1462-evaluating-ai-models-for-code-comprehension) - [Coffee with Developers - Maria Apazoglou](https://www.wearedevelopers.com/videos/1209-coffee-with-developers-maria-apazoglou) - [Why your codebase lies to AI?](https://www.wearedevelopers.com/videos/100281-why-your-codebase-lies-to-ai) - [How to become an AI toolsmith](https://www.wearedevelopers.com/videos/653-how-to-become-an-ai-toolsmith) ## Related Articles - [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models) - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this) - [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)