> Markdown version of [/jobs/ext/4326293-software-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4326293-software-ai-engineer). 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).

---

# Software AI Engineer

- **Company:** Improving
- **Location:** Dallas, TX, United States
- **Contract:** Permanent contract
- **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Code Review, Programming Tools, Software Reliability Testing, Software Engineering, Large Language Models, Agentic-AI, Build Management, Data Analytics, Codebase, Claude, Virtual Agents, Google Gemini
- **Published:** October 31, 2026
- **Apply:** https://www.careerbuilder.com/job-details/software-ai-engineer-dallas-tx--3a7f0cf3-1fde-43ca-9d3a-636433d0f9e9

## About the Role

Artificial Intelligence (AI), Software Engineering, Artificial Intelligence (AI), Programming Tools, Application Programming Interface (API), Reliability Testing, Technical Leadership, Mentoring, Code Reviews, Artificial Intelligence (AI) Agents, * Deep, hands-on experience building AI agents or agentic systems in production

 * Strong understanding of LLM capabilities and limitations across multiple models (Claude, Gemini, Llama, etc.)
 * Expertise in prompt engineering, model selection, and working with tool-use/function calling
 * Proven ability to architect systems that are reliable, maintainable, and performant at scale
 * Staff-level impact: You have led significant technical initiatives and elevated team capabilities

Preferred

 * Experience with multi-step reasoning, chain-of-thought patterns, or complex agent workflows
 * Familiarity with evaluation frameworks for agentic systems
 * Background in developer tools, productivity platforms, or engineering analytics
 * Understanding of the practical tradeoffs in production agentic systems

## Description

* Design and build AI agent architectures that interact with development tools, codebases, and team workflows in meaningful ways
 * Work extensively with LLM APIs (Claude, Gemini, Llama, and others) to understand their capabilities, limitations, and optimal application patterns
 * Drive agent quality and reliability through systematic testing, safety mechanisms, and feedback loops with real users
 * Own the developer experience of agentic interactions-making complex AI capabilities feel natural and trustworthy
 * Lead technical decision-making on agent patterns, model selection, and integration approaches
 * Mentor and raise the bar across the team through code review, architecture guidance, and knowledge sharing