Full Stack Software Engineer

Full Stack Software Engineer - AI -Austin TX / Warren MI


About the Role


We are seeking an innovative Full Stack Software Engineer with specialized expertise in Artificial Intelligence to drive the development of our next-generation applications. In this role, you will own the end-to-end lifecycle of new features, building highly scalable Java backends and dynamic React frontends while integrating cutting-edge LLMs and AI frameworks.


You will be expected to make critical architectural decisions, balance model trade-offs (cost, latency, accuracy), and leverage AI-assisted tooling to accelerate development.


Key Responsibilities

• End-to-End Engineering: Architect, build, and deploy robust full-stack solutions, designing everything from the data model and API structure to the user interface flow.
• Backend Development: Build scalable APIs, microservices, and batch-processing systems utilizing Java .
• Frontend Development: Own and develop intuitive, responsive UIs for dashboards, internal tools, and public-facing applications using React .
• AI & LLM Integration: Design and implement AI-powered features (e.g., RAG systems, AI agents, chatbots, recommendation engines) into production environments.
• Model Management: Evaluate, select, and integrate appropriate AI models (OpenAI, Anthropic Claude, Gemini, Llama) and handle optimization for latency, accuracy, and operational cost.
• Modern Workflows: Utilize modern AI-assisted development tools (e.g., Cursor, GitHub Copilot, Claude Code) to improve code quality, validate outputs, and enhance engineering velocity.

Required Skills & Qualifications

• Backend Expertise: Strong professional experience in Java ecosystem architecture and microservices development.
• Frontend Expertise: Proven track record of owning frontend architecture and delivering complex UIs in React.
• AI/ML Frameworks: Hands-on experience with the modern AI stack, including LangChain , LlamaIndex , Hugging Face , and Vector Databases .
• System Design: Exceptional ability to conceptualize new services from the ground up, making sound architectural choices across the entire stack.
• Problem Solving: Demonstrated ability to navigate the unique technical challenges of AI implementation, including prompt engineering, context window limits, and output validation.

Application Questionnaire


To help us better understand your background and approach to engineering, please provide brief, specific answers (a few sentences each) to the following questions along with your application:

1. AI-assisted development tools: Which AI-assisted development tools have you used (e.g., Cursor, GitHub Copilot, Claude Code, ChatGPT)? Describe a specific task where one of these tools meaningfully changed how you worked-what you asked it to do, how you validated its output, and where you found it fell short.
2. Building AI-powered applications: Have you built any applications that use AI or LLMs (e.g., a chatbot, RAG system, summarizer, agent, recommendation feature)? Pick one project and walk us through what it did, your role, the architecture, and the hardest technical problem you had to solve.
3. Models, APIs, and frameworks: Which AI models and platforms have you worked with (e.g., OpenAI GPT, Anthropic Claude, Llama, Gemini, or open-source models), and which frameworks or tools (e.g., LangChain, LlamaIndex, vector databases, Hugging Face)? How did you decide which model or approach was right for a given problem, and how did you handle cost, latency, or accuracy trade-offs?
4. Java / Backend Experience: What kinds of backend systems have you built with Java (e.g., APIs, microservices, batch jobs), and what were your primary responsibilities on those projects?
5. React / Frontend Experience: What types of React applications have you worked on (dashboards, internal tools, public sites), and which parts of the UI or front-end architecture did you own?
6. System Design / Thinking: When you start a new feature or service, how do you typically approach deciding the overall design (APIs, data model, front-end flow) at a high level?